Axis Spatial

Terminus-2 – Qwen 3.8 27B (xhigh) vs. Claude Code – Claude Sonnet 5.5 (high): geospatial agent comparison

Comparison between Terminus-2 – Qwen 3.8 27B (xhigh) and Claude Code – Claude Sonnet 5.5 (high) on the Geospatial Agent Index, each benchmark, cost, time and token use, from the same tasks, agent and limits. Methodology.

Side by side

Terminus-2 – Qwen 3.8 27B (xhigh) vs. Claude Code – Claude Sonnet 5.5 (high)
MetricTerminus-2 – Qwen 3.8 27B (xhigh)Claude Code – Claude Sonnet 5.5 (high)
Geospatial Agent Index62* (partial: 0.3 of 3 attempts)81* (partial: 1.9 of 3 attempts)
GeoAgentBench score60100
GeoBenchX scoreNo data67
Earth-Bench score2758
GeoAnalystBench score10097
Raster and remote sensing score3679
Vector and overlay score7881
Networks and routing score67100
Climate and time series score4379
Spatial statistics and interpolation score6273
Mapping and cartography score10076
Recognising infeasible requests scoreNo data61
Cost per task$0.066$0.062
Time per task19.8 min0.7 min
Tokens per attempt90k95k
Turns per attempt8.24.6
Attempts decided101479
Input price per 1M tokens$0.45$2.00
Output price per 1M tokens$3.20$10.00
Context window262,144No data
Image inputYesNo data
DeveloperAlibaba (Qwen)Anthropic

Charts

Geospatial Agent Index

Equal-weight average of the evaluation scores, 0 to 100 · Higher is better

  • Partial coverage
Geospatial Agent IndexClaude Code – Claude Sonnet 5.5 (high): 81* (partial coverage); Terminus-2 – Qwen 3.8 27B (xhigh): 62* (partial coverage)025507510081*Claude Sonnet 5.5 (high)62*Qwen 3.8 27B (xhigh)
Data table: Geospatial Agent Index
Geospatial Agent Index
ModelCreatorGeospatial Agent IndexRange while attempts are pendingBenchmarks coveredCoverage (attempts)
Claude Code – Claude Sonnet 5.5 (high)Anthropic81* (partial: 1.9 of 3 attempts)71 to 824 of 4479 of 870 planned attempts (236 excluded)
Terminus-2 – Qwen 3.8 27B (xhigh)Alibaba (Qwen)62* (partial: 0.3 of 3 attempts)No pending judgements; coverage incomplete3 of 4101 of 870 planned attempts

Cost per task

Average cost per task (USD) · Lower is better

  • Partial coverage
Cost per taskClaude Code – Claude Sonnet 5.5 (high): $0.062 (partial coverage); Terminus-2 – Qwen 3.8 27B (xhigh): $0.066 (partial coverage)$0$0.020$0.040$0.060$0.080$0.062Claude Sonnet 5.5 (high)$0.066Qwen 3.8 27B (xhigh)
Data table: Cost per task
Cost per task
ModelCreatorCost per taskCoverage (attempts)
Terminus-2 – Qwen 3.8 27B (xhigh)Alibaba (Qwen)$0.066101 of 870 planned attempts
Claude Code – Claude Sonnet 5.5 (high)Anthropic$0.062543 of 870 planned attempts (236 excluded)

Time per task

Average agent wall time per task · Lower is better

  • Partial coverage
Time per taskClaude Code – Claude Sonnet 5.5 (high): 0.7 min (partial coverage); Terminus-2 – Qwen 3.8 27B (xhigh): 19.8 min (partial coverage)0m5m10m15m20m0.7 minClaude Sonnet 5.5 (high)19.8 minQwen 3.8 27B (xhigh)
Data table: Time per task
Time per task
ModelCreatorTime per taskCoverage (attempts)
Terminus-2 – Qwen 3.8 27B (xhigh)Alibaba (Qwen)19.8 min101 of 870 planned attempts
Claude Code – Claude Sonnet 5.5 (high)Anthropic0.7 min543 of 870 planned attempts (236 excluded)

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Terminus-2 – Qwen 3.8 27B (xhigh) or Claude Code – Claude Sonnet 5.5 (high)?
Not comparable yet: Terminus-2 – Qwen 3.8 27B (xhigh) has scores on 3 of 4 benchmarks, so it is not yet ranked. Terminus-2 – Qwen 3.8 27B (xhigh): 101 of 870 planned attempts. Claude Code – Claude Sonnet 5.5 (high): 479 of 870 planned attempts (236 excluded). Coverage is partial; scores can change as more attempts are decided.
Which is cheaper per task, Terminus-2 – Qwen 3.8 27B (xhigh) or Claude Code – Claude Sonnet 5.5 (high)?
Claude Code – Claude Sonnet 5.5 (high), at $0.062 against $0.066 for Terminus-2 – Qwen 3.8 27B (xhigh).
Which is faster per task, Terminus-2 – Qwen 3.8 27B (xhigh) or Claude Code – Claude Sonnet 5.5 (high)?
Claude Code – Claude Sonnet 5.5 (high), at 0.7 min against 19.8 min for Terminus-2 – Qwen 3.8 27B (xhigh).
Which has the larger context window, Terminus-2 – Qwen 3.8 27B (xhigh) or Claude Code – Claude Sonnet 5.5 (high)?
Not known yet: Claude Code – Claude Sonnet 5.5 (high) has no context window data.

More: Terminus-2 – Qwen 3.8 27B (xhigh) · Claude Code – Claude Sonnet 5.5 (high) · all comparisons