{ "schema_version": 1, "name": "Geospatial Agent Benchmarks", "publisher": "Axis Spatial", "url": "https://www.axisspatial.com/arena", "generated_at": "2026-10-09 15:44 UTC", "methodology": { "version": "0.5", "url": "https://www.axisspatial.com/arena/methodology" }, "scope": "Results come from file-based geospatial analysis tasks: the agent reads rasters and vectors with code, computes, and makes maps. Image interpretation, where the model has to look at an image to answer, is not covered.", "definitions": { "score": "0 to 100: average task pass@1 over decided attempts; null means no data.", "index": "Equal-weight average of benchmark scores. Ranked only when every benchmark has a score; ranking eligibility does not imply complete attempt coverage.", "coverage": "Counts of attempts, with three attempts planned per task. Incomplete coverage means scores can change as more attempts are decided.", "cost_per_task_usd": "Mean recorded cost per attempt, in US dollars; null means no data.", "time_per_task_seconds": "Mean recorded agent time per attempt, in seconds; null means no data.", "pending_score_range": "Score bounds while recorded attempts await judgement; does not include unrun attempts." }, "benchmarks": [ { "name": "GeoAgentBench", "url": "https://www.axisspatial.com/arena/evaluations/geoagentbench", "source": "https://github.com/geox-lab/GABench", "tasks": 50 }, { "name": "GeoBenchX", "url": "https://www.axisspatial.com/arena/evaluations/geobenchx", "source": "https://github.com/Solirinai/GeoBenchX", "tasks": 173 }, { "name": "Earth-Bench", "url": "https://www.axisspatial.com/arena/evaluations/earth-bench", "source": "https://github.com/opendatalab/Earth-Agent", "tasks": 48 }, { "name": "GeoAnalystBench", "url": "https://www.axisspatial.com/arena/evaluations/geoanalystbench", "source": "https://github.com/GeoDS/GeoAnalystBench", "tasks": 19 } ], "models": [ { "slug": "deepseek-v4-flash-high", "name": "DeepSeek V4 Flash (high)", "entry": "Terminus-2 – DeepSeek V4 Flash (high)", "developer": "DeepSeek", "harness": "Terminus-2", "reasoning": "high", "url": "https://www.axisspatial.com/arena/models/deepseek-v4-flash-high", "index": { "score": 71.17, "coverage": { "with_data": 181, "planned": 870, "run": 181, "counted": 181, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 177, "cost_per_task_usd": 0.059391, "cost_coverage": { "with_data": 181, "planned": 870, "run": 181, "counted": 181, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 590.5, "time_coverage": { "with_data": 181, "planned": 870, "run": 181, "counted": 181, "pending": 0, "excluded": 0, "complete": false }, "ranking_eligible": true }, "benchmarks": { "GeoAgentBench": { "score": 96.0, "coverage": { "with_data": 50, "planned": 150, "run": 50, "counted": 50, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 50, "cost_per_task_usd": 0.02629, "cost_coverage": { "with_data": 50, "planned": 150, "run": 50, "counted": 50, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 322.6, "time_coverage": { "with_data": 50, "planned": 150, "run": 50, "counted": 50, "pending": 0, "excluded": 0, "complete": false } }, "GeoBenchX": { "score": 46.67, "coverage": { "with_data": 60, "planned": 519, "run": 60, "counted": 60, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 60, "cost_per_task_usd": 0.061873, "cost_coverage": { "with_data": 60, "planned": 519, "run": 60, "counted": 60, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 524.8, "time_coverage": { "with_data": 60, "planned": 519, "run": 60, "counted": 60, "pending": 0, "excluded": 0, "complete": false } }, "Earth-Bench": { "score": 42.01, "coverage": { "with_data": 52, "planned": 144, "run": 52, "counted": 52, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 48, "cost_per_task_usd": 0.101652, "cost_coverage": { "with_data": 52, "planned": 144, "run": 52, "counted": 52, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 1038.5, "time_coverage": { "with_data": 52, "planned": 144, "run": 52, "counted": 52, "pending": 0, "excluded": 0, "complete": false } }, "GeoAnalystBench": { "score": 100.0, "coverage": { "with_data": 19, "planned": 57, "run": 19, "counted": 19, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 19, "cost_per_task_usd": 0.022994, "cost_coverage": { "with_data": 19, "planned": 57, "run": 19, "counted": 19, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 277.4, "time_coverage": { "with_data": 19, "planned": 57, "run": 19, "counted": 19, "pending": 0, "excluded": 0, "complete": false } } }, "breakdowns": { "kind_of_work": { "raster-and-remote-sensing": { "name": "Raster and remote sensing", "tasks": 75, "score": 67.41, "coverage": { "with_data": 70, "planned": 225, "run": 70, "counted": 70, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 67, "cost_per_task_usd": 0.06874, "cost_coverage": { "with_data": 70, "planned": 225, "run": 70, "counted": 70, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 689.1, "time_coverage": { "with_data": 70, "planned": 225, "run": 70, "counted": 70, "pending": 0, "excluded": 0, "complete": false } }, "vector-and-overlay": { "name": "Vector and overlay", "tasks": 18, "score": 75.0, "coverage": { "with_data": 16, "planned": 54, "run": 16, "counted": 16, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 16, "cost_per_task_usd": 0.046579, "cost_coverage": { "with_data": 16, "planned": 54, "run": 16, "counted": 16, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 524.9, "time_coverage": { "with_data": 16, "planned": 54, "run": 16, "counted": 16, "pending": 0, "excluded": 0, "complete": false } }, "networks-and-routing": { "name": "Networks and routing", "tasks": 5, "score": 100.0, "coverage": { "with_data": 5, "planned": 15, "run": 5, "counted": 5, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 5, "cost_per_task_usd": 0.03546, "cost_coverage": { "with_data": 5, "planned": 15, "run": 5, "counted": 5, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 418.9, "time_coverage": { "with_data": 5, "planned": 15, "run": 5, "counted": 5, "pending": 0, "excluded": 0, "complete": false } }, "climate-and-time-series": { "name": "Climate and time series", "tasks": 24, "score": 66.67, "coverage": { "with_data": 25, "planned": 72, "run": 25, "counted": 25, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 24, "cost_per_task_usd": 0.073171, "cost_coverage": { "with_data": 25, "planned": 72, "run": 25, "counted": 25, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 811.6, "time_coverage": { "with_data": 25, "planned": 72, "run": 25, "counted": 25, "pending": 0, "excluded": 0, "complete": false } }, "spatial-statistics-and-interpolation": { "name": "Spatial statistics and interpolation", "tasks": 24, "score": 73.33, "coverage": { "with_data": 15, "planned": 72, "run": 15, "counted": 15, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 15, "cost_per_task_usd": 0.043272, "cost_coverage": { "with_data": 15, "planned": 72, "run": 15, "counted": 15, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 383.1, "time_coverage": { "with_data": 15, "planned": 72, "run": 15, "counted": 15, "pending": 0, "excluded": 0, "complete": false } }, "mapping-and-cartography": { "name": "Mapping and cartography", "tasks": 65, "score": 75.0, "coverage": { "with_data": 20, "planned": 195, "run": 20, "counted": 20, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 20, "cost_per_task_usd": 0.042741, "cost_coverage": { "with_data": 20, "planned": 195, "run": 20, "counted": 20, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 411.7, "time_coverage": { "with_data": 20, "planned": 195, "run": 20, "counted": 20, "pending": 0, "excluded": 0, "complete": false } }, "recognising-infeasible-requests": { "name": "Recognising infeasible requests", "tasks": 79, "score": 36.67, "coverage": { "with_data": 30, "planned": 237, "run": 30, "counted": 30, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 30, "cost_per_task_usd": 0.056072, "cost_coverage": { "with_data": 30, "planned": 237, "run": 30, "counted": 30, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 463.0, "time_coverage": { "with_data": 30, "planned": 237, "run": 30, "counted": 30, "pending": 0, "excluded": 0, "complete": false } } }, "task_format": { "multi-step-analysis": { "name": "Multi-step analysis", "tasks": 151, "score": 87.1, "coverage": { "with_data": 93, "planned": 453, "run": 93, "counted": 93, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 93, "cost_per_task_usd": 0.033619, "cost_coverage": { "with_data": 93, "planned": 453, "run": 93, "counted": 93, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 362.2, "time_coverage": { "with_data": 93, "planned": 453, "run": 93, "counted": 93, "pending": 0, "excluded": 0, "complete": false } }, "single-answer-questions": { "name": "Single-answer questions", "tasks": 60, "score": 42.9, "coverage": { "with_data": 58, "planned": 180, "run": 58, "counted": 58, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 54, "cost_per_task_usd": 0.10243, "cost_coverage": { "with_data": 58, "planned": 180, "run": 58, "counted": 58, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 1022.6, "time_coverage": { "with_data": 58, "planned": 180, "run": 58, "counted": 58, "pending": 0, "excluded": 0, "complete": false } }, "recognising-infeasible-requests": { "name": "Recognising infeasible requests", "tasks": 79, "score": 36.67, "coverage": { "with_data": 30, "planned": 237, "run": 30, "counted": 30, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 30, "cost_per_task_usd": 0.056072, "cost_coverage": { "with_data": 30, "planned": 237, "run": 30, "counted": 30, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 463.0, "time_coverage": { "with_data": 30, "planned": 237, "run": 30, "counted": 30, "pending": 0, "excluded": 0, "complete": false } } } } }, { "slug": "deepseek-v4-pro-high", "name": "DeepSeek V4 Pro (high)", "entry": "Terminus-2 – DeepSeek V4 Pro (high)", "developer": "DeepSeek", "harness": "Terminus-2", "reasoning": "high", "url": "https://www.axisspatial.com/arena/models/deepseek-v4-pro-high", "index": { "score": 72.92, "coverage": { "with_data": 209, "planned": 870, "run": 209, "counted": 209, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 200, "cost_per_task_usd": 0.264605, "cost_coverage": { "with_data": 209, "planned": 870, "run": 209, "counted": 209, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 513.5, "time_coverage": { "with_data": 209, "planned": 870, "run": 209, "counted": 209, "pending": 0, "excluded": 0, "complete": false }, "ranking_eligible": true }, "benchmarks": { "GeoAgentBench": { "score": 98.0, "coverage": { "with_data": 50, "planned": 150, "run": 50, "counted": 50, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 50, "cost_per_task_usd": 0.091269, "cost_coverage": { "with_data": 50, "planned": 150, "run": 50, "counted": 50, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 329.3, "time_coverage": { "with_data": 50, "planned": 150, "run": 50, "counted": 50, "pending": 0, "excluded": 0, "complete": false } }, "GeoBenchX": { "score": 45.78, "coverage": { "with_data": 83, "planned": 519, "run": 83, "counted": 83, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 83, "cost_per_task_usd": 0.293623, "cost_coverage": { "with_data": 83, "planned": 519, "run": 83, "counted": 83, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 443.7, "time_coverage": { "with_data": 83, "planned": 519, "run": 83, "counted": 83, "pending": 0, "excluded": 0, "complete": false } }, "Earth-Bench": { "score": 47.92, "coverage": { "with_data": 57, "planned": 144, "run": 57, "counted": 57, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 48, "cost_per_task_usd": 0.433655, "cost_coverage": { "with_data": 57, "planned": 144, "run": 57, "counted": 57, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 881.3, "time_coverage": { "with_data": 57, "planned": 144, "run": 57, "counted": 57, "pending": 0, "excluded": 0, "complete": false } }, "GeoAnalystBench": { "score": 100.0, "coverage": { "with_data": 19, "planned": 57, "run": 19, "counted": 19, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 19, "cost_per_task_usd": 0.086842, "cost_coverage": { "with_data": 19, "planned": 57, "run": 19, "counted": 19, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 199.3, "time_coverage": { "with_data": 19, "planned": 57, "run": 19, "counted": 19, "pending": 0, "excluded": 0, "complete": false } } }, "breakdowns": { "kind_of_work": { "raster-and-remote-sensing": { "name": "Raster and remote sensing", "tasks": 75, "score": 74.02, "coverage": { "with_data": 73, "planned": 225, "run": 73, "counted": 73, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 68, "cost_per_task_usd": 0.251558, "cost_coverage": { "with_data": 73, "planned": 225, "run": 73, "counted": 73, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 584.0, "time_coverage": { "with_data": 73, "planned": 225, "run": 73, "counted": 73, "pending": 0, "excluded": 0, "complete": false } }, "vector-and-overlay": { "name": "Vector and overlay", "tasks": 18, "score": 70.59, "coverage": { "with_data": 17, "planned": 54, "run": 17, "counted": 17, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 17, "cost_per_task_usd": 0.191593, "cost_coverage": { "with_data": 17, "planned": 54, "run": 17, "counted": 17, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 426.9, "time_coverage": { "with_data": 17, "planned": 54, "run": 17, "counted": 17, "pending": 0, "excluded": 0, "complete": false } }, "networks-and-routing": { "name": "Networks and routing", "tasks": 5, "score": 100.0, "coverage": { "with_data": 5, "planned": 15, "run": 5, "counted": 5, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 5, "cost_per_task_usd": 0.122845, "cost_coverage": { "with_data": 5, "planned": 15, "run": 5, "counted": 5, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 401.8, "time_coverage": { "with_data": 5, "planned": 15, "run": 5, "counted": 5, "pending": 0, "excluded": 0, "complete": false } }, "climate-and-time-series": { "name": "Climate and time series", "tasks": 24, "score": 65.28, "coverage": { "with_data": 28, "planned": 72, "run": 28, "counted": 28, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 24, "cost_per_task_usd": 0.427918, "cost_coverage": { "with_data": 28, "planned": 72, "run": 28, "counted": 28, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 767.1, "time_coverage": { "with_data": 28, "planned": 72, "run": 28, "counted": 28, "pending": 0, "excluded": 0, "complete": false } }, "spatial-statistics-and-interpolation": { "name": "Spatial statistics and interpolation", "tasks": 24, "score": 52.94, "coverage": { "with_data": 17, "planned": 72, "run": 17, "counted": 17, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 17, "cost_per_task_usd": 0.216544, "cost_coverage": { "with_data": 17, "planned": 72, "run": 17, "counted": 17, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 407.4, "time_coverage": { "with_data": 17, "planned": 72, "run": 17, "counted": 17, "pending": 0, "excluded": 0, "complete": false } }, "mapping-and-cartography": { "name": "Mapping and cartography", "tasks": 65, "score": 68.97, "coverage": { "with_data": 29, "planned": 195, "run": 29, "counted": 29, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 29, "cost_per_task_usd": 0.224964, "cost_coverage": { "with_data": 29, "planned": 195, "run": 29, "counted": 29, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 342.0, "time_coverage": { "with_data": 29, "planned": 195, "run": 29, "counted": 29, "pending": 0, "excluded": 0, "complete": false } }, "recognising-infeasible-requests": { "name": "Recognising infeasible requests", "tasks": 79, "score": 42.5, "coverage": { "with_data": 40, "planned": 237, "run": 40, "counted": 40, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 40, "cost_per_task_usd": 0.272015, "cost_coverage": { "with_data": 40, "planned": 237, "run": 40, "counted": 40, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 427.3, "time_coverage": { "with_data": 40, "planned": 237, "run": 40, "counted": 40, "pending": 0, "excluded": 0, "complete": false } } }, "task_format": { "multi-step-analysis": { "name": "Multi-step analysis", "tasks": 151, "score": 82.86, "coverage": { "with_data": 105, "planned": 453, "run": 105, "counted": 105, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 105, "cost_per_task_usd": 0.157687, "cost_coverage": { "with_data": 105, "planned": 453, "run": 105, "counted": 105, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 336.3, "time_coverage": { "with_data": 105, "planned": 453, "run": 105, "counted": 105, "pending": 0, "excluded": 0, "complete": false } }, "single-answer-questions": { "name": "Single-answer questions", "tasks": 60, "score": 45.45, "coverage": { "with_data": 64, "planned": 180, "run": 64, "counted": 64, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 55, "cost_per_task_usd": 0.435387, "cost_coverage": { "with_data": 64, "planned": 180, "run": 64, "counted": 64, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 858.0, "time_coverage": { "with_data": 64, "planned": 180, "run": 64, "counted": 64, "pending": 0, "excluded": 0, "complete": false } }, "recognising-infeasible-requests": { "name": "Recognising infeasible requests", "tasks": 79, "score": 42.5, "coverage": { "with_data": 40, "planned": 237, "run": 40, "counted": 40, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 40, "cost_per_task_usd": 0.272015, "cost_coverage": { "with_data": 40, "planned": 237, "run": 40, "counted": 40, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 427.3, "time_coverage": { "with_data": 40, "planned": 237, "run": 40, "counted": 40, "pending": 0, "excluded": 0, "complete": false } } } } }, { "slug": "gemma-4-26b-a4b-thinking-on", "name": "Gemma 4 26B A4B (thinking on)", "entry": "Terminus-2 – Gemma 4 26B A4B (thinking on)", "developer": "Google", "harness": "Terminus-2", "reasoning": "thinking on", "url": "https://www.axisspatial.com/arena/models/gemma-4-26b-a4b-thinking-on", "index": { "score": 60.76, "coverage": { "with_data": 209, "planned": 870, "run": 210, "counted": 209, "pending": 1, "excluded": 0, "complete": false }, "pending_score_range": { "min": 60.59, "max": 60.77 }, "judgement_status": "61 to 61", "tasks_with_decided_attempts": 138, "cost_per_task_usd": 0.014118, "cost_coverage": { "with_data": 210, "planned": 870, "run": 210, "counted": 209, "pending": 1, "excluded": 0, "complete": false }, "time_per_task_seconds": 699.4, "time_coverage": { "with_data": 210, "planned": 870, "run": 210, "counted": 209, "pending": 1, "excluded": 0, "complete": false }, "ranking_eligible": true }, "benchmarks": { "GeoAgentBench": { "score": 85.71, "coverage": { "with_data": 49, "planned": 150, "run": 49, "counted": 49, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 49, "cost_per_task_usd": 0.011568, "cost_coverage": { "with_data": 49, "planned": 150, "run": 49, "counted": 49, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 309.0, "time_coverage": { "with_data": 49, "planned": 150, "run": 49, "counted": 49, "pending": 0, "excluded": 0, "complete": false } }, "GeoBenchX": { "score": 54.55, "coverage": { "with_data": 22, "planned": 519, "run": 22, "counted": 22, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 22, "cost_per_task_usd": 0.011962, "cost_coverage": { "with_data": 22, "planned": 519, "run": 22, "counted": 22, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 201.5, "time_coverage": { "with_data": 22, "planned": 519, "run": 22, "counted": 22, "pending": 0, "excluded": 0, "complete": false } }, "Earth-Bench": { "score": 34.37, "coverage": { "with_data": 119, "planned": 144, "run": 120, "counted": 119, "pending": 1, "excluded": 0, "complete": false }, "pending_score_range": { "min": 33.68, "max": 34.38 }, "judgement_status": "34 to 34", "tasks_with_decided_attempts": 48, "cost_per_task_usd": 0.016647, "cost_coverage": { "with_data": 120, "planned": 144, "run": 120, "counted": 119, "pending": 1, "excluded": 0, "complete": false }, "time_per_task_seconds": 1020.8, "time_coverage": { "with_data": 120, "planned": 144, "run": 120, "counted": 119, "pending": 1, "excluded": 0, "complete": false } }, "GeoAnalystBench": { "score": 68.42, "coverage": { "with_data": 19, "planned": 57, "run": 19, "counted": 19, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 19, "cost_per_task_usd": 0.007224, "cost_coverage": { "with_data": 19, "planned": 57, "run": 19, "counted": 19, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 252.8, "time_coverage": { "with_data": 19, "planned": 57, "run": 19, "counted": 19, "pending": 0, "excluded": 0, "complete": false } } }, "breakdowns": { "kind_of_work": { "raster-and-remote-sensing": { "name": "Raster and remote sensing", "tasks": 75, "score": 53.17, "coverage": { "with_data": 107, "planned": 225, "run": 108, "counted": 107, "pending": 1, "excluded": 0, "complete": false }, "pending_score_range": { "min": 52.65, "max": 53.17 }, "judgement_status": "53 to 53", "tasks_with_decided_attempts": 63, "cost_per_task_usd": 0.014045, "cost_coverage": { "with_data": 108, "planned": 225, "run": 108, "counted": 107, "pending": 1, "excluded": 0, "complete": false }, "time_per_task_seconds": 849.2, "time_coverage": { "with_data": 108, "planned": 225, "run": 108, "counted": 107, "pending": 1, "excluded": 0, "complete": false } }, "vector-and-overlay": { "name": "Vector and overlay", "tasks": 18, "score": 78.57, "coverage": { "with_data": 14, "planned": 54, "run": 14, "counted": 14, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 14, "cost_per_task_usd": 0.017657, "cost_coverage": { "with_data": 14, "planned": 54, "run": 14, "counted": 14, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 357.5, "time_coverage": { "with_data": 14, "planned": 54, "run": 14, "counted": 14, "pending": 0, "excluded": 0, "complete": false } }, "networks-and-routing": { "name": "Networks and routing", "tasks": 5, "score": 100.0, "coverage": { "with_data": 4, "planned": 15, "run": 4, "counted": 4, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 4, "cost_per_task_usd": 0.015735, "cost_coverage": { "with_data": 4, "planned": 15, "run": 4, "counted": 4, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 404.7, "time_coverage": { "with_data": 4, "planned": 15, "run": 4, "counted": 4, "pending": 0, "excluded": 0, "complete": false } }, "climate-and-time-series": { "name": "Climate and time series", "tasks": 24, "score": 50.0, "coverage": { "with_data": 51, "planned": 72, "run": 51, "counted": 51, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 24, "cost_per_task_usd": 0.015985, "cost_coverage": { "with_data": 51, "planned": 72, "run": 51, "counted": 51, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 804.3, "time_coverage": { "with_data": 51, "planned": 72, "run": 51, "counted": 51, "pending": 0, "excluded": 0, "complete": false } }, "spatial-statistics-and-interpolation": { "name": "Spatial statistics and interpolation", "tasks": 24, "score": 75.0, "coverage": { "with_data": 12, "planned": 72, "run": 12, "counted": 12, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 12, "cost_per_task_usd": 0.008853, "cost_coverage": { "with_data": 12, "planned": 72, "run": 12, "counted": 12, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 281.5, "time_coverage": { "with_data": 12, "planned": 72, "run": 12, "counted": 12, "pending": 0, "excluded": 0, "complete": false } }, "mapping-and-cartography": { "name": "Mapping and cartography", "tasks": 65, "score": 83.33, "coverage": { "with_data": 12, "planned": 195, "run": 12, "counted": 12, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 12, "cost_per_task_usd": 0.009448, "cost_coverage": { "with_data": 12, "planned": 195, "run": 12, "counted": 12, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 181.6, "time_coverage": { "with_data": 12, "planned": 195, "run": 12, "counted": 12, "pending": 0, "excluded": 0, "complete": false } }, "recognising-infeasible-requests": { "name": "Recognising infeasible requests", "tasks": 79, "score": 44.44, "coverage": { "with_data": 9, "planned": 237, "run": 9, "counted": 9, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 9, "cost_per_task_usd": 0.011443, "cost_coverage": { "with_data": 9, "planned": 237, "run": 9, "counted": 9, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 217.6, "time_coverage": { "with_data": 9, "planned": 237, "run": 9, "counted": 9, "pending": 0, "excluded": 0, "complete": false } } }, "task_format": { "multi-step-analysis": { "name": "Multi-step analysis", "tasks": 151, "score": 78.21, "coverage": { "with_data": 78, "planned": 453, "run": 78, "counted": 78, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 78, "cost_per_task_usd": 0.010603, "cost_coverage": { "with_data": 78, "planned": 453, "run": 78, "counted": 78, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 280.2, "time_coverage": { "with_data": 78, "planned": 453, "run": 78, "counted": 78, "pending": 0, "excluded": 0, "complete": false } }, "single-answer-questions": { "name": "Single-answer questions", "tasks": 60, "score": 36.27, "coverage": { "with_data": 122, "planned": 180, "run": 123, "counted": 122, "pending": 1, "excluded": 0, "complete": false }, "pending_score_range": { "min": 35.62, "max": 36.27 }, "judgement_status": "36 to 36", "tasks_with_decided_attempts": 51, "cost_per_task_usd": 0.016543, "cost_coverage": { "with_data": 123, "planned": 180, "run": 123, "counted": 122, "pending": 1, "excluded": 0, "complete": false }, "time_per_task_seconds": 1000.5, "time_coverage": { "with_data": 123, "planned": 180, "run": 123, "counted": 122, "pending": 1, "excluded": 0, "complete": false } }, "recognising-infeasible-requests": { "name": "Recognising infeasible requests", "tasks": 79, "score": 44.44, "coverage": { "with_data": 9, "planned": 237, "run": 9, "counted": 9, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 9, "cost_per_task_usd": 0.011443, "cost_coverage": { "with_data": 9, "planned": 237, "run": 9, "counted": 9, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 217.6, "time_coverage": { "with_data": 9, "planned": 237, "run": 9, "counted": 9, "pending": 0, "excluded": 0, "complete": false } } } } }, { "slug": "glm-4-7-flash-thinking-on", "name": "GLM-4.7-Flash (thinking on)", "entry": "Terminus-2 – GLM-4.7-Flash (thinking on)", "developer": "Z.ai", "harness": "Terminus-2", "reasoning": "thinking on", "url": "https://www.axisspatial.com/arena/models/glm-4-7-flash-thinking-on", "index": { "score": 40.57, "coverage": { "with_data": 176, "planned": 870, "run": 176, "counted": 176, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 150, "cost_per_task_usd": 0.026539, "cost_coverage": { "with_data": 176, "planned": 870, "run": 176, "counted": 176, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 600.4, "time_coverage": { "with_data": 176, "planned": 870, "run": 176, "counted": 176, "pending": 0, "excluded": 0, "complete": false }, "ranking_eligible": true }, "benchmarks": { "GeoAgentBench": { "score": 36.0, "coverage": { "with_data": 50, "planned": 150, "run": 50, "counted": 50, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 50, "cost_per_task_usd": 0.023197, "cost_coverage": { "with_data": 50, "planned": 150, "run": 50, "counted": 50, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 670.7, "time_coverage": { "with_data": 50, "planned": 150, "run": 50, "counted": 50, "pending": 0, "excluded": 0, "complete": false } }, "GeoBenchX": { "score": 39.39, "coverage": { "with_data": 33, "planned": 519, "run": 33, "counted": 33, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 33, "cost_per_task_usd": 0.023324, "cost_coverage": { "with_data": 33, "planned": 519, "run": 33, "counted": 33, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 399.2, "time_coverage": { "with_data": 33, "planned": 519, "run": 33, "counted": 33, "pending": 0, "excluded": 0, "complete": false } }, "Earth-Bench": { "score": 44.79, "coverage": { "with_data": 74, "planned": 144, "run": 74, "counted": 74, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 48, "cost_per_task_usd": 0.032553, "cost_coverage": { "with_data": 74, "planned": 144, "run": 74, "counted": 74, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 683.7, "time_coverage": { "with_data": 74, "planned": 144, "run": 74, "counted": 74, "pending": 0, "excluded": 0, "complete": false } }, "GeoAnalystBench": { "score": 42.11, "coverage": { "with_data": 19, "planned": 57, "run": 19, "counted": 19, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 19, "cost_per_task_usd": 0.017499, "cost_coverage": { "with_data": 19, "planned": 57, "run": 19, "counted": 19, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 440.6, "time_coverage": { "with_data": 19, "planned": 57, "run": 19, "counted": 19, "pending": 0, "excluded": 0, "complete": false } } }, "breakdowns": { "kind_of_work": { "raster-and-remote-sensing": { "name": "Raster and remote sensing", "tasks": 75, "score": 35.9, "coverage": { "with_data": 84, "planned": 225, "run": 84, "counted": 84, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 65, "cost_per_task_usd": 0.027075, "cost_coverage": { "with_data": 84, "planned": 225, "run": 84, "counted": 84, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 661.7, "time_coverage": { "with_data": 84, "planned": 225, "run": 84, "counted": 84, "pending": 0, "excluded": 0, "complete": false } }, "vector-and-overlay": { "name": "Vector and overlay", "tasks": 18, "score": 35.71, "coverage": { "with_data": 14, "planned": 54, "run": 14, "counted": 14, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 14, "cost_per_task_usd": 0.033402, "cost_coverage": { "with_data": 14, "planned": 54, "run": 14, "counted": 14, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 605.3, "time_coverage": { "with_data": 14, "planned": 54, "run": 14, "counted": 14, "pending": 0, "excluded": 0, "complete": false } }, "networks-and-routing": { "name": "Networks and routing", "tasks": 5, "score": 20.0, "coverage": { "with_data": 5, "planned": 15, "run": 5, "counted": 5, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 5, "cost_per_task_usd": 0.034964, "cost_coverage": { "with_data": 5, "planned": 15, "run": 5, "counted": 5, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 1032.2, "time_coverage": { "with_data": 5, "planned": 15, "run": 5, "counted": 5, "pending": 0, "excluded": 0, "complete": false } }, "climate-and-time-series": { "name": "Climate and time series", "tasks": 24, "score": 54.86, "coverage": { "with_data": 31, "planned": 72, "run": 31, "counted": 31, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 24, "cost_per_task_usd": 0.029763, "cost_coverage": { "with_data": 31, "planned": 72, "run": 31, "counted": 31, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 681.6, "time_coverage": { "with_data": 31, "planned": 72, "run": 31, "counted": 31, "pending": 0, "excluded": 0, "complete": false } }, "spatial-statistics-and-interpolation": { "name": "Spatial statistics and interpolation", "tasks": 24, "score": 40.0, "coverage": { "with_data": 15, "planned": 72, "run": 15, "counted": 15, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 15, "cost_per_task_usd": 0.018448, "cost_coverage": { "with_data": 15, "planned": 72, "run": 15, "counted": 15, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 402.1, "time_coverage": { "with_data": 15, "planned": 72, "run": 15, "counted": 15, "pending": 0, "excluded": 0, "complete": false } }, "mapping-and-cartography": { "name": "Mapping and cartography", "tasks": 65, "score": 53.85, "coverage": { "with_data": 13, "planned": 195, "run": 13, "counted": 13, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 13, "cost_per_task_usd": 0.01128, "cost_coverage": { "with_data": 13, "planned": 195, "run": 13, "counted": 13, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 184.2, "time_coverage": { "with_data": 13, "planned": 195, "run": 13, "counted": 13, "pending": 0, "excluded": 0, "complete": false } }, "recognising-infeasible-requests": { "name": "Recognising infeasible requests", "tasks": 79, "score": 35.71, "coverage": { "with_data": 14, "planned": 237, "run": 14, "counted": 14, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 14, "cost_per_task_usd": 0.029152, "cost_coverage": { "with_data": 14, "planned": 237, "run": 14, "counted": 14, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 492.4, "time_coverage": { "with_data": 14, "planned": 237, "run": 14, "counted": 14, "pending": 0, "excluded": 0, "complete": false } } }, "task_format": { "multi-step-analysis": { "name": "Multi-step analysis", "tasks": 151, "score": 38.82, "coverage": { "with_data": 85, "planned": 453, "run": 85, "counted": 85, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 85, "cost_per_task_usd": 0.021146, "cost_coverage": { "with_data": 85, "planned": 453, "run": 85, "counted": 85, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 550.1, "time_coverage": { "with_data": 85, "planned": 453, "run": 85, "counted": 85, "pending": 0, "excluded": 0, "complete": false } }, "single-answer-questions": { "name": "Single-answer questions", "tasks": 60, "score": 44.12, "coverage": { "with_data": 77, "planned": 180, "run": 77, "counted": 77, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 51, "cost_per_task_usd": 0.032018, "cost_coverage": { "with_data": 77, "planned": 180, "run": 77, "counted": 77, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 675.6, "time_coverage": { "with_data": 77, "planned": 180, "run": 77, "counted": 77, "pending": 0, "excluded": 0, "complete": false } }, "recognising-infeasible-requests": { "name": "Recognising infeasible requests", "tasks": 79, "score": 35.71, "coverage": { "with_data": 14, "planned": 237, "run": 14, "counted": 14, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 14, "cost_per_task_usd": 0.029152, "cost_coverage": { "with_data": 14, "planned": 237, "run": 14, "counted": 14, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 492.4, "time_coverage": { "with_data": 14, "planned": 237, "run": 14, "counted": 14, "pending": 0, "excluded": 0, "complete": false } } } } }, { "slug": "gpt-oss-120b-high", "name": "gpt-oss-120b (high)", "entry": "Terminus-2 – gpt-oss-120b (high)", "developer": "OpenAI", "harness": "Terminus-2", "reasoning": "high", "url": "https://www.axisspatial.com/arena/models/gpt-oss-120b-high", "index": { "score": 52.2, "coverage": { "with_data": 320, "planned": 870, "run": 321, "counted": 320, "pending": 1, "excluded": 0, "complete": false }, "pending_score_range": { "min": 51.94, "max": 52.2 }, "judgement_status": "52 to 52", "tasks_with_decided_attempts": 262, "cost_per_task_usd": 0.02509, "cost_coverage": { "with_data": 321, "planned": 870, "run": 321, "counted": 320, "pending": 1, "excluded": 0, "complete": false }, "time_per_task_seconds": 266.3, "time_coverage": { "with_data": 321, "planned": 870, "run": 321, "counted": 320, "pending": 1, "excluded": 0, "complete": false }, "ranking_eligible": true }, "benchmarks": { "GeoAgentBench": { "score": 70.0, "coverage": { "with_data": 50, "planned": 150, "run": 50, "counted": 50, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 50, "cost_per_task_usd": 0.02275, "cost_coverage": { "with_data": 50, "planned": 150, "run": 50, "counted": 50, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 352.6, "time_coverage": { "with_data": 50, "planned": 150, "run": 50, "counted": 50, "pending": 0, "excluded": 0, "complete": false } }, "GeoBenchX": { "score": 40.69, "coverage": { "with_data": 145, "planned": 519, "run": 145, "counted": 145, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 145, "cost_per_task_usd": 0.021774, "cost_coverage": { "with_data": 145, "planned": 519, "run": 145, "counted": 145, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 223.4, "time_coverage": { "with_data": 145, "planned": 519, "run": 145, "counted": 145, "pending": 0, "excluded": 0, "complete": false } }, "Earth-Bench": { "score": 45.49, "coverage": { "with_data": 106, "planned": 144, "run": 107, "counted": 106, "pending": 1, "excluded": 0, "complete": false }, "pending_score_range": { "min": 44.44, "max": 45.49 }, "judgement_status": "44 to 45", "tasks_with_decided_attempts": 48, "cost_per_task_usd": 0.031857, "cost_coverage": { "with_data": 107, "planned": 144, "run": 107, "counted": 106, "pending": 1, "excluded": 0, "complete": false }, "time_per_task_seconds": 293.3, "time_coverage": { "with_data": 107, "planned": 144, "run": 107, "counted": 106, "pending": 1, "excluded": 0, "complete": false } }, "GeoAnalystBench": { "score": 52.63, "coverage": { "with_data": 19, "planned": 57, "run": 19, "counted": 19, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 19, "cost_per_task_usd": 0.018441, "cost_coverage": { "with_data": 19, "planned": 57, "run": 19, "counted": 19, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 215.2, "time_coverage": { "with_data": 19, "planned": 57, "run": 19, "counted": 19, "pending": 0, "excluded": 0, "complete": false } } }, "breakdowns": { "kind_of_work": { "raster-and-remote-sensing": { "name": "Raster and remote sensing", "tasks": 75, "score": 52.03, "coverage": { "with_data": 111, "planned": 225, "run": 112, "counted": 111, "pending": 1, "excluded": 0, "complete": false }, "pending_score_range": { "min": 51.35, "max": 52.03 }, "judgement_status": "51 to 52", "tasks_with_decided_attempts": 74, "cost_per_task_usd": 0.027318, "cost_coverage": { "with_data": 112, "planned": 225, "run": 112, "counted": 111, "pending": 1, "excluded": 0, "complete": false }, "time_per_task_seconds": 283.3, "time_coverage": { "with_data": 112, "planned": 225, "run": 112, "counted": 111, "pending": 1, "excluded": 0, "complete": false } }, "vector-and-overlay": { "name": "Vector and overlay", "tasks": 18, "score": 55.56, "coverage": { "with_data": 18, "planned": 54, "run": 18, "counted": 18, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 18, "cost_per_task_usd": 0.025572, "cost_coverage": { "with_data": 18, "planned": 54, "run": 18, "counted": 18, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 299.3, "time_coverage": { "with_data": 18, "planned": 54, "run": 18, "counted": 18, "pending": 0, "excluded": 0, "complete": false } }, "networks-and-routing": { "name": "Networks and routing", "tasks": 5, "score": 100.0, "coverage": { "with_data": 5, "planned": 15, "run": 5, "counted": 5, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 5, "cost_per_task_usd": 0.029677, "cost_coverage": { "with_data": 5, "planned": 15, "run": 5, "counted": 5, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 660.0, "time_coverage": { "with_data": 5, "planned": 15, "run": 5, "counted": 5, "pending": 0, "excluded": 0, "complete": false } }, "climate-and-time-series": { "name": "Climate and time series", "tasks": 24, "score": 59.72, "coverage": { "with_data": 45, "planned": 72, "run": 45, "counted": 45, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 24, "cost_per_task_usd": 0.032238, "cost_coverage": { "with_data": 45, "planned": 72, "run": 45, "counted": 45, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 322.7, "time_coverage": { "with_data": 45, "planned": 72, "run": 45, "counted": 45, "pending": 0, "excluded": 0, "complete": false } }, "spatial-statistics-and-interpolation": { "name": "Spatial statistics and interpolation", "tasks": 24, "score": 28.57, "coverage": { "with_data": 21, "planned": 72, "run": 21, "counted": 21, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 21, "cost_per_task_usd": 0.017003, "cost_coverage": { "with_data": 21, "planned": 72, "run": 21, "counted": 21, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 203.9, "time_coverage": { "with_data": 21, "planned": 72, "run": 21, "counted": 21, "pending": 0, "excluded": 0, "complete": false } }, "mapping-and-cartography": { "name": "Mapping and cartography", "tasks": 65, "score": 40.0, "coverage": { "with_data": 50, "planned": 195, "run": 50, "counted": 50, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 50, "cost_per_task_usd": 0.02351, "cost_coverage": { "with_data": 50, "planned": 195, "run": 50, "counted": 50, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 231.1, "time_coverage": { "with_data": 50, "planned": 195, "run": 50, "counted": 50, "pending": 0, "excluded": 0, "complete": false } }, "recognising-infeasible-requests": { "name": "Recognising infeasible requests", "tasks": 79, "score": 45.71, "coverage": { "with_data": 70, "planned": 237, "run": 70, "counted": 70, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 70, "cost_per_task_usd": 0.020032, "cost_coverage": { "with_data": 70, "planned": 237, "run": 70, "counted": 70, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 210.2, "time_coverage": { "with_data": 70, "planned": 237, "run": 70, "counted": 70, "pending": 0, "excluded": 0, "complete": false } } }, "task_format": { "multi-step-analysis": { "name": "Multi-step analysis", "tasks": 151, "score": 50.76, "coverage": { "with_data": 132, "planned": 453, "run": 132, "counted": 132, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 132, "cost_per_task_usd": 0.022746, "cost_coverage": { "with_data": 132, "planned": 453, "run": 132, "counted": 132, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 275.6, "time_coverage": { "with_data": 132, "planned": 453, "run": 132, "counted": 132, "pending": 0, "excluded": 0, "complete": false } }, "single-answer-questions": { "name": "Single-answer questions", "tasks": 60, "score": 44.72, "coverage": { "with_data": 118, "planned": 180, "run": 119, "counted": 118, "pending": 1, "excluded": 0, "complete": false }, "pending_score_range": { "min": 43.89, "max": 44.72 }, "judgement_status": "44 to 45", "tasks_with_decided_attempts": 60, "cost_per_task_usd": 0.030665, "cost_coverage": { "with_data": 119, "planned": 180, "run": 119, "counted": 118, "pending": 1, "excluded": 0, "complete": false }, "time_per_task_seconds": 289.1, "time_coverage": { "with_data": 119, "planned": 180, "run": 119, "counted": 118, "pending": 1, "excluded": 0, "complete": false } }, "recognising-infeasible-requests": { "name": "Recognising infeasible requests", "tasks": 79, "score": 45.71, "coverage": { "with_data": 70, "planned": 237, "run": 70, "counted": 70, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 70, "cost_per_task_usd": 0.020032, "cost_coverage": { "with_data": 70, "planned": 237, "run": 70, "counted": 70, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 210.2, "time_coverage": { "with_data": 70, "planned": 237, "run": 70, "counted": 70, "pending": 0, "excluded": 0, "complete": false } } } } }, { "slug": "kimi-k2-7-code-always-on", "name": "Kimi K2.7 Code (always on)", "entry": "Terminus-2 – Kimi K2.7 Code (always on)", "developer": "Moonshot AI", "harness": "Terminus-2", "reasoning": "always on", "url": "https://www.axisspatial.com/arena/models/kimi-k2-7-code-always-on", "index": { "score": 72.78, "coverage": { "with_data": 268, "planned": 870, "run": 269, "counted": 268, "pending": 1, "excluded": 0, "complete": false }, "pending_score_range": { "min": 72.52, "max": 72.78 }, "judgement_status": "73 to 73", "tasks_with_decided_attempts": 264, "cost_per_task_usd": 0.128706, "cost_coverage": { "with_data": 269, "planned": 870, "run": 269, "counted": 268, "pending": 1, "excluded": 0, "complete": false }, "time_per_task_seconds": 406.5, "time_coverage": { "with_data": 269, "planned": 870, "run": 269, "counted": 268, "pending": 1, "excluded": 0, "complete": false }, "ranking_eligible": true }, "benchmarks": { "GeoAgentBench": { "score": 90.0, "coverage": { "with_data": 50, "planned": 150, "run": 50, "counted": 50, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 50, "cost_per_task_usd": 0.038477, "cost_coverage": { "with_data": 50, "planned": 150, "run": 50, "counted": 50, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 179.6, "time_coverage": { "with_data": 50, "planned": 150, "run": 50, "counted": 50, "pending": 0, "excluded": 0, "complete": false } }, "GeoBenchX": { "score": 55.1, "coverage": { "with_data": 147, "planned": 519, "run": 147, "counted": 147, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 147, "cost_per_task_usd": 0.1136, "cost_coverage": { "with_data": 147, "planned": 519, "run": 147, "counted": 147, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 384.7, "time_coverage": { "with_data": 147, "planned": 519, "run": 147, "counted": 147, "pending": 0, "excluded": 0, "complete": false } }, "Earth-Bench": { "score": 61.81, "coverage": { "with_data": 52, "planned": 144, "run": 53, "counted": 52, "pending": 1, "excluded": 0, "complete": false }, "pending_score_range": { "min": 60.76, "max": 61.81 }, "judgement_status": "61 to 62", "tasks_with_decided_attempts": 48, "cost_per_task_usd": 0.287557, "cost_coverage": { "with_data": 53, "planned": 144, "run": 53, "counted": 52, "pending": 1, "excluded": 0, "complete": false }, "time_per_task_seconds": 739.3, "time_coverage": { "with_data": 53, "planned": 144, "run": 53, "counted": 52, "pending": 1, "excluded": 0, "complete": false } }, "GeoAnalystBench": { "score": 84.21, "coverage": { "with_data": 19, "planned": 57, "run": 19, "counted": 19, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 19, "cost_per_task_usd": 0.039911, "cost_coverage": { "with_data": 19, "planned": 57, "run": 19, "counted": 19, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 244.6, "time_coverage": { "with_data": 19, "planned": 57, "run": 19, "counted": 19, "pending": 0, "excluded": 0, "complete": false } } }, "breakdowns": { "kind_of_work": { "raster-and-remote-sensing": { "name": "Raster and remote sensing", "tasks": 75, "score": 73.87, "coverage": { "with_data": 78, "planned": 225, "run": 78, "counted": 78, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 74, "cost_per_task_usd": 0.182882, "cost_coverage": { "with_data": 78, "planned": 225, "run": 78, "counted": 78, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 533.4, "time_coverage": { "with_data": 78, "planned": 225, "run": 78, "counted": 78, "pending": 0, "excluded": 0, "complete": false } }, "vector-and-overlay": { "name": "Vector and overlay", "tasks": 18, "score": 77.78, "coverage": { "with_data": 18, "planned": 54, "run": 18, "counted": 18, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 18, "cost_per_task_usd": 0.055952, "cost_coverage": { "with_data": 18, "planned": 54, "run": 18, "counted": 18, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 303.6, "time_coverage": { "with_data": 18, "planned": 54, "run": 18, "counted": 18, "pending": 0, "excluded": 0, "complete": false } }, "networks-and-routing": { "name": "Networks and routing", "tasks": 5, "score": 80.0, "coverage": { "with_data": 5, "planned": 15, "run": 5, "counted": 5, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 5, "cost_per_task_usd": 0.04878, "cost_coverage": { "with_data": 5, "planned": 15, "run": 5, "counted": 5, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 204.8, "time_coverage": { "with_data": 5, "planned": 15, "run": 5, "counted": 5, "pending": 0, "excluded": 0, "complete": false } }, "climate-and-time-series": { "name": "Climate and time series", "tasks": 24, "score": 79.17, "coverage": { "with_data": 24, "planned": 72, "run": 25, "counted": 24, "pending": 1, "excluded": 0, "complete": false }, "pending_score_range": { "min": 77.08, "max": 79.17 }, "judgement_status": "77 to 79", "tasks_with_decided_attempts": 24, "cost_per_task_usd": 0.183412, "cost_coverage": { "with_data": 25, "planned": 72, "run": 25, "counted": 24, "pending": 1, "excluded": 0, "complete": false }, "time_per_task_seconds": 507.4, "time_coverage": { "with_data": 25, "planned": 72, "run": 25, "counted": 24, "pending": 1, "excluded": 0, "complete": false } }, "spatial-statistics-and-interpolation": { "name": "Spatial statistics and interpolation", "tasks": 24, "score": 66.67, "coverage": { "with_data": 21, "planned": 72, "run": 21, "counted": 21, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 21, "cost_per_task_usd": 0.105723, "cost_coverage": { "with_data": 21, "planned": 72, "run": 21, "counted": 21, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 383.3, "time_coverage": { "with_data": 21, "planned": 72, "run": 21, "counted": 21, "pending": 0, "excluded": 0, "complete": false } }, "mapping-and-cartography": { "name": "Mapping and cartography", "tasks": 65, "score": 72.55, "coverage": { "with_data": 51, "planned": 195, "run": 51, "counted": 51, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 51, "cost_per_task_usd": 0.085901, "cost_coverage": { "with_data": 51, "planned": 195, "run": 51, "counted": 51, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 283.2, "time_coverage": { "with_data": 51, "planned": 195, "run": 51, "counted": 51, "pending": 0, "excluded": 0, "complete": false } }, "recognising-infeasible-requests": { "name": "Recognising infeasible requests", "tasks": 79, "score": 40.85, "coverage": { "with_data": 71, "planned": 237, "run": 71, "counted": 71, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 71, "cost_per_task_usd": 0.111544, "cost_coverage": { "with_data": 71, "planned": 237, "run": 71, "counted": 71, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 367.4, "time_coverage": { "with_data": 71, "planned": 237, "run": 71, "counted": 71, "pending": 0, "excluded": 0, "complete": false } } }, "task_format": { "multi-step-analysis": { "name": "Multi-step analysis", "tasks": 151, "score": 80.45, "coverage": { "with_data": 133, "planned": 453, "run": 133, "counted": 133, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 133, "cost_per_task_usd": 0.073407, "cost_coverage": { "with_data": 133, "planned": 453, "run": 133, "counted": 133, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 280.2, "time_coverage": { "with_data": 133, "planned": 453, "run": 133, "counted": 133, "pending": 0, "excluded": 0, "complete": false } }, "single-answer-questions": { "name": "Single-answer questions", "tasks": 60, "score": 59.44, "coverage": { "with_data": 64, "planned": 180, "run": 65, "counted": 64, "pending": 1, "excluded": 0, "complete": false }, "pending_score_range": { "min": 58.61, "max": 59.44 }, "judgement_status": "59 to 59", "tasks_with_decided_attempts": 60, "cost_per_task_usd": 0.260602, "cost_coverage": { "with_data": 65, "planned": 180, "run": 65, "counted": 64, "pending": 1, "excluded": 0, "complete": false }, "time_per_task_seconds": 707.8, "time_coverage": { "with_data": 65, "planned": 180, "run": 65, "counted": 64, "pending": 1, "excluded": 0, "complete": false } }, "recognising-infeasible-requests": { "name": "Recognising infeasible requests", "tasks": 79, "score": 40.85, "coverage": { "with_data": 71, "planned": 237, "run": 71, "counted": 71, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 71, "cost_per_task_usd": 0.111544, "cost_coverage": { "with_data": 71, "planned": 237, "run": 71, "counted": 71, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 367.4, "time_coverage": { "with_data": 71, "planned": 237, "run": 71, "counted": 71, "pending": 0, "excluded": 0, "complete": false } } } } }, { "slug": "qwen-3-8-27b-xhigh", "name": "Qwen 3.8 27B (xhigh)", "entry": "Terminus-2 – Qwen 3.8 27B (xhigh)", "developer": "Alibaba (Qwen)", "harness": "Terminus-2", "reasoning": "xhigh", "url": "https://www.axisspatial.com/arena/models/qwen-3-8-27b-xhigh", "index": { "score": 62.5, "coverage": { "with_data": 101, "planned": 870, "run": 101, "counted": 101, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 101, "cost_per_task_usd": 0.065915, "cost_coverage": { "with_data": 101, "planned": 870, "run": 101, "counted": 101, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 1185.0, "time_coverage": { "with_data": 101, "planned": 870, "run": 101, "counted": 101, "pending": 0, "excluded": 0, "complete": false }, "ranking_eligible": false }, "benchmarks": { "GeoAgentBench": { "score": 60.42, "coverage": { "with_data": 48, "planned": 150, "run": 48, "counted": 48, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 48, "cost_per_task_usd": 0.070436, "cost_coverage": { "with_data": 48, "planned": 150, "run": 48, "counted": 48, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 1110.5, "time_coverage": { "with_data": 48, "planned": 150, "run": 48, "counted": 48, "pending": 0, "excluded": 0, "complete": false } }, "GeoBenchX": { "score": null, "coverage": { "with_data": 0, "planned": 519, "run": 0, "counted": 0, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No data", "tasks_with_decided_attempts": 0, "cost_per_task_usd": null, "cost_coverage": { "with_data": 0, "planned": 519, "run": 0, "counted": 0, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": null, "time_coverage": { "with_data": 0, "planned": 519, "run": 0, "counted": 0, "pending": 0, "excluded": 0, "complete": false } }, "Earth-Bench": { "score": 27.08, "coverage": { "with_data": 48, "planned": 144, "run": 48, "counted": 48, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 48, "cost_per_task_usd": 0.060461, "cost_coverage": { "with_data": 48, "planned": 144, "run": 48, "counted": 48, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 1316.2, "time_coverage": { "with_data": 48, "planned": 144, "run": 48, "counted": 48, "pending": 0, "excluded": 0, "complete": false } }, "GeoAnalystBench": { "score": 100.0, "coverage": { "with_data": 5, "planned": 57, "run": 5, "counted": 5, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 5, "cost_per_task_usd": 0.074873, "cost_coverage": { "with_data": 5, "planned": 57, "run": 5, "counted": 5, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 640.2, "time_coverage": { "with_data": 5, "planned": 57, "run": 5, "counted": 5, "pending": 0, "excluded": 0, "complete": false } } }, "breakdowns": { "kind_of_work": { "raster-and-remote-sensing": { "name": "Raster and remote sensing", "tasks": 75, "score": 35.71, "coverage": { "with_data": 56, "planned": 225, "run": 56, "counted": 56, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 56, "cost_per_task_usd": 0.052475, "cost_coverage": { "with_data": 56, "planned": 225, "run": 56, "counted": 56, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 1362.4, "time_coverage": { "with_data": 56, "planned": 225, "run": 56, "counted": 56, "pending": 0, "excluded": 0, "complete": false } }, "vector-and-overlay": { "name": "Vector and overlay", "tasks": 18, "score": 77.78, "coverage": { "with_data": 9, "planned": 54, "run": 9, "counted": 9, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 9, "cost_per_task_usd": 0.086372, "cost_coverage": { "with_data": 9, "planned": 54, "run": 9, "counted": 9, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 1078.2, "time_coverage": { "with_data": 9, "planned": 54, "run": 9, "counted": 9, "pending": 0, "excluded": 0, "complete": false } }, "networks-and-routing": { "name": "Networks and routing", "tasks": 5, "score": 66.67, "coverage": { "with_data": 3, "planned": 15, "run": 3, "counted": 3, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 3, "cost_per_task_usd": 0.152339, "cost_coverage": { "with_data": 3, "planned": 15, "run": 3, "counted": 3, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 879.8, "time_coverage": { "with_data": 3, "planned": 15, "run": 3, "counted": 3, "pending": 0, "excluded": 0, "complete": false } }, "climate-and-time-series": { "name": "Climate and time series", "tasks": 24, "score": 42.86, "coverage": { "with_data": 21, "planned": 72, "run": 21, "counted": 21, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 21, "cost_per_task_usd": 0.075742, "cost_coverage": { "with_data": 21, "planned": 72, "run": 21, "counted": 21, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 1041.1, "time_coverage": { "with_data": 21, "planned": 72, "run": 21, "counted": 21, "pending": 0, "excluded": 0, "complete": false } }, "spatial-statistics-and-interpolation": { "name": "Spatial statistics and interpolation", "tasks": 24, "score": 62.5, "coverage": { "with_data": 8, "planned": 72, "run": 8, "counted": 8, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 8, "cost_per_task_usd": 0.086758, "cost_coverage": { "with_data": 8, "planned": 72, "run": 8, "counted": 8, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 965.8, "time_coverage": { "with_data": 8, "planned": 72, "run": 8, "counted": 8, "pending": 0, "excluded": 0, "complete": false } }, "mapping-and-cartography": { "name": "Mapping and cartography", "tasks": 65, "score": 100.0, "coverage": { "with_data": 4, "planned": 195, "run": 4, "counted": 4, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 4, "cost_per_task_usd": 0.049954, "cost_coverage": { "with_data": 4, "planned": 195, "run": 4, "counted": 4, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 364.1, "time_coverage": { "with_data": 4, "planned": 195, "run": 4, "counted": 4, "pending": 0, "excluded": 0, "complete": false } }, "recognising-infeasible-requests": { "name": "Recognising infeasible requests", "tasks": 79, "score": null, "coverage": { "with_data": 0, "planned": 237, "run": 0, "counted": 0, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No data", "tasks_with_decided_attempts": 0, "cost_per_task_usd": null, "cost_coverage": { "with_data": 0, "planned": 237, "run": 0, "counted": 0, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": null, "time_coverage": { "with_data": 0, "planned": 237, "run": 0, "counted": 0, "pending": 0, "excluded": 0, "complete": false } } }, "task_format": { "multi-step-analysis": { "name": "Multi-step analysis", "tasks": 151, "score": 64.15, "coverage": { "with_data": 53, "planned": 453, "run": 53, "counted": 53, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 53, "cost_per_task_usd": 0.070854, "cost_coverage": { "with_data": 53, "planned": 453, "run": 53, "counted": 53, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 1066.2, "time_coverage": { "with_data": 53, "planned": 453, "run": 53, "counted": 53, "pending": 0, "excluded": 0, "complete": false } }, "single-answer-questions": { "name": "Single-answer questions", "tasks": 60, "score": 27.08, "coverage": { "with_data": 48, "planned": 180, "run": 48, "counted": 48, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No pending judgements; coverage incomplete", "tasks_with_decided_attempts": 48, "cost_per_task_usd": 0.060461, "cost_coverage": { "with_data": 48, "planned": 180, "run": 48, "counted": 48, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": 1316.2, "time_coverage": { "with_data": 48, "planned": 180, "run": 48, "counted": 48, "pending": 0, "excluded": 0, "complete": false } }, "recognising-infeasible-requests": { "name": "Recognising infeasible requests", "tasks": 79, "score": null, "coverage": { "with_data": 0, "planned": 237, "run": 0, "counted": 0, "pending": 0, "excluded": 0, "complete": false }, "pending_score_range": null, "judgement_status": "No data", "tasks_with_decided_attempts": 0, "cost_per_task_usd": null, "cost_coverage": { "with_data": 0, "planned": 237, "run": 0, "counted": 0, "pending": 0, "excluded": 0, "complete": false }, "time_per_task_seconds": null, "time_coverage": { "with_data": 0, "planned": 237, "run": 0, "counted": 0, "pending": 0, "excluded": 0, "complete": false } } } } } ] }