Experimental run record
Run 90a4a241
An inspectable execution record: configuration, deterministic outcomes, attempts, artefacts, and failure traces. Comparison applies across the configurations in this run only.
· pack geoworkbench-0.1 · accepted · sealed snapshot 3199b999
- Trials
- 12
- Accepted
- 8
- Configurations
- 4
- Tasks
- 3
- Cost USD
- 0.02152
In shortKimi K2.6 led this run: 2/3 tasks accepted (66.7%) for 0.0043 USD total. This ranking holds inside this run only — it is not a general model ranking.
| # | Model | Architecture | Accepted | Rate | First-attempt success | False-success rejected | Cost USD | Cost / accepted | Median ms | p95 ms |
|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Kimi K2.6 | single-shot | 2/3 | 66.7% | 66.7% | 1 | 0.0043 | 0.0021 | 31950 ms | 47663 ms |
| 2 | GLM-4.7 Flash | single-shot | 2/3 | 66.7% | 66.7% | 1 | 0.0044 | 0.0022 | 32054 ms | 55953 ms |
| 3 | GLM-4.7 Flash | single-retry | 2/3 | 66.7% | 66.7% | 1 | 0.0063 | 0.0032 | 26260 ms | 87049 ms |
| 4 | Kimi K2.6 | single-retry | 2/3 | 66.7% | 66.7% | 1 | 0.0065 | 0.0032 | 44513 ms | 85304 ms |
Trials
attempt traces expand beneath each trial| Task | Configuration | Retry | Result | Attempts | Cost USD | Latency ms |
|---|---|---|---|---|---|---|
| crs-reproject-munich | GLM-4.7 Flash | single-shot | accepted | 1 | 0.0015 USD | 32054 ms |
Attempt trace undefined# attempt undefined — model: @cf/zai-org/glm-4.7-flash — exit 0 — accepted — cost 0.0015 USD — 32054 ms # verifier: PASS — CRS reproject to WGS84 verified # artifact: download (591 bytes) import geopandas as gpd # Load the input data gdf = gpd.read_file("input.geojson") # Diagnose CRS: Large coordinates indicate Web Mercator (EPSG:3857) gdf.crs = "EPSG:3857" # Reproject to WGS84 (EPSG:4326) gdf_wgs84 = gdf.to_crs("EPSG:4326") # Write the result gdf_wgs84.to_file("output.geojson", driver="GeoJSON") | ||||||
| crs-reproject-munich | GLM-4.7 Flash | single-retry | accepted | 1 | 0.0013 USD | 26040 ms |
Attempt trace undefined# attempt undefined — model: @cf/zai-org/glm-4.7-flash — exit 0 — accepted — cost 0.0013 USD — 26040 ms # verifier: PASS — CRS reproject to WGS84 verified # artifact: download (591 bytes) import geopandas as gpd # Load the input file gdf = gpd.read_file("input.geojson") # Diagnose and assign CRS # The prompt indicates coordinates are large (millions), indicating a projected CRS. # We are instructed to determine the CRS is EPSG:3857. gdf.crs = "EPSG:3857" # Reproject to WGS84 (EPSG:4326) gdf_wgs84 = gdf.to_crs("EPSG:4326") # Write the result to output.geojson gdf_wgs84.to_file("output.geojson", driver="GeoJSON") | ||||||
| raster-zonal-mean | GLM-4.7 Flash | single-shot | rejected | 1 | 0.0019 USD | 55953 ms |
Attempt trace undefined# attempt undefined — model: @cf/zai-org/glm-4.7-flash — exit 0 — rejected — cost 0.0019 USD — 55953 ms
# verifier: FAIL — stats.json unreadable
# no artifact produced
| ||||||
| raster-zonal-mean | GLM-4.7 Flash | single-retry | rejected | 2 | 0.0038 USD | 87049 ms |
Attempt trace undefined# attempt undefined — model: @cf/zai-org/glm-4.7-flash — exit 0 — rejected — cost 0.0019 USD — 38014 ms
# verifier: FAIL — stats.json unreadable
# no artifact produced
Attempt trace undefined# attempt undefined — model: @cf/zai-org/glm-4.7-flash — exit 0 — rejected — cost 0.0019 USD — 87049 ms
# verifier: FAIL — stats.json unreadable
# no artifact produced
| ||||||
| vector-buffer-1km | GLM-4.7 Flash | single-shot | accepted | 1 | 0.0010 USD | 23259 ms |
Attempt trace undefined# attempt undefined — model: @cf/zai-org/glm-4.7-flash — exit 0 — accepted — cost 0.0010 USD — 23259 ms # verifier: PASS — 1000m buffers verified # artifact: download (5935 bytes) import geopandas as gpd gdf = gpd.read_file("sites.geojson") gdf_projected = gdf.to_crs(epsg=3857) gdf_projected['geometry'] = gdf_projected.buffer(1000) gdf_final = gdf_projected.to_crs(epsg=4326) gdf_final.to_file("buffers.geojson", driver="GeoJSON") | ||||||
| vector-buffer-1km | GLM-4.7 Flash | single-retry | accepted | 1 | 0.0012 USD | 26260 ms |
Attempt trace undefined# attempt undefined — model: @cf/zai-org/glm-4.7-flash — exit 0 — accepted — cost 0.0012 USD — 26260 ms # verifier: PASS — 1000m buffers verified # artifact: download (5903 bytes) import geopandas as gpd # Read the input file gdf = gpd.read_file("sites.geojson") # Reproject to EPSG:3857 (Web Mercator) for accurate 1000m buffering gdf_projected = gdf.to_crs(epsg=3857) # Create 1000m buffers gdf_projected['buffer'] = gdf_projected.geometry.buffer(1000) # Extract the buffer geometries and reproject back to EPSG:4326 buffers_gdf = gpd.GeoDataFrame(geometry=gdf_projected['buffer'], crs="EPSG:3857") buffers_gdf = buffers_gdf.to_crs(epsg=4326) # Write the output buffers_gdf.to_file("buffers.geojson", driver="GeoJSON") | ||||||
| crs-reproject-munich | Kimi K2.6 | single-shot | accepted | 1 | 0.0012 USD | 31950 ms |
Attempt trace undefined# attempt undefined — model: @cf/moonshotai/kimi-k2.6 — exit 0 — accepted — cost 0.0012 USD — 31950 ms # verifier: PASS — CRS reproject to WGS84 verified # artifact: download (591 bytes) import geopandas as gpd gdf = gpd.read_file("input.geojson") gdf = gdf.set_crs(epsg=3857, allow_override=True) gdf = gdf.to_crs(epsg=4326) gdf.to_file("output.geojson", driver="GeoJSON") | ||||||
| crs-reproject-munich | Kimi K2.6 | single-retry | accepted | 1 | 0.0017 USD | 44513 ms |
Attempt trace undefined# attempt undefined — model: @cf/moonshotai/kimi-k2.6 — exit 0 — accepted — cost 0.0017 USD — 44513 ms # verifier: PASS — CRS reproject to WGS84 verified # artifact: download (591 bytes) import geopandas as gpd gdf = gpd.read_file("input.geojson") gdf = gdf.set_crs(epsg=3857, allow_override=True) gdf = gdf.to_crs(epsg=4326) gdf.to_file("output.geojson", driver="GeoJSON") | ||||||
| raster-zonal-mean | Kimi K2.6 | single-shot | rejected | 1 | 0.0019 USD | 47663 ms |
Attempt trace undefined# attempt undefined — model: @cf/moonshotai/kimi-k2.6 — exit 0 — rejected — cost 0.0019 USD — 47663 ms
# verifier: FAIL — stats.json unreadable
# no artifact produced
| ||||||
| raster-zonal-mean | Kimi K2.6 | single-retry | rejected | 2 | 0.0038 USD | 85304 ms |
Attempt trace undefined# attempt undefined — model: @cf/moonshotai/kimi-k2.6 — exit 0 — rejected — cost 0.0019 USD — 38181 ms
# verifier: FAIL — stats.json unreadable
# no artifact produced
Attempt trace undefined# attempt undefined — model: @cf/moonshotai/kimi-k2.6 — exit 0 — rejected — cost 0.0019 USD — 85304 ms
# verifier: FAIL — stats.json unreadable
# no artifact produced
| ||||||
| vector-buffer-1km | Kimi K2.6 | single-shot | accepted | 1 | 0.0011 USD | 30670 ms |
Attempt trace undefined# attempt undefined — model: @cf/moonshotai/kimi-k2.6 — exit 0 — accepted — cost 0.0011 USD — 30670 ms # verifier: PASS — 1000m buffers verified # artifact: download (5935 bytes) import geopandas as gpd gdf = gpd.read_file("sites.geojson") gdf = gdf.set_crs("EPSG:4326", allow_override=True) gdf_proj = gdf.to_crs("EPSG:3857") gdf_proj["geometry"] = gdf_proj.buffer(1000) gdf_out = gdf_proj.to_crs("EPSG:4326") gdf_out.to_file("buffers.geojson", driver="GeoJSON") | ||||||
| vector-buffer-1km | Kimi K2.6 | single-retry | accepted | 1 | 0.0010 USD | 24427 ms |
Attempt trace undefined# attempt undefined — model: @cf/moonshotai/kimi-k2.6 — exit 0 — accepted — cost 0.0010 USD — 24427 ms # verifier: PASS — 1000m buffers verified # artifact: download (5935 bytes) import geopandas as gpd gdf = gpd.read_file("sites.geojson") if gdf.crs is None: gdf.set_crs(epsg=4326, inplace=True) gdf_proj = gdf.to_crs(epsg=3857) gdf_proj["geometry"] = gdf_proj.buffer(1000) gdf_wgs84 = gdf_proj.to_crs(epsg=4326) gdf_wgs84.to_file("buffers.geojson", driver="GeoJSON") | ||||||
Cite this record
Axis Spatial. "Experimental run 90a4a241." Axis Spatial Arena, run 90a4a241-8f55-4b8c-921c-9ddfaa8f2ea2. Benchmark pack geoworkbench-0.1. https://www.axisspatial.com/arena/runs/90a4a241-8f55-4b8c-921c-9ddfaa8f2ea2 (accessed 19 Sep 2026).
@misc{axis-spatial-arena-run-90a4a241,
author = {{Axis Spatial}},
title = {Experimental run 90a4a241},
howpublished = {Axis Spatial Arena, run: https://www.axisspatial.com/arena/runs/90a4a241-8f55-4b8c-921c-9ddfaa8f2ea2},
note = {Benchmark pack geoworkbench-0.1},
year = {2026}
}Glossary
full protocol in the methodology- Pack version
- The pinned set of task definitions a run executed. Results from different pack versions are never compared directly.
- Configuration
- A complete comparison unit: model, prompt version, tools, retry policy, and pinned task, data, and verifier versions. A model name alone is not comparable.
- Lane
- One configured route through which a model is reached. Duplicate upstream models across lanes count as adapter evidence, not extra capability.
- False-success rejection
- A trial whose output looked plausible but failed independent deterministic checks, such as an empty file or a fabricated value.
- Token-cost proxy
- Cost estimated from reported token usage and list prices at recording time; actual billing may differ.
- Sealed snapshot
- An immutable, content-addressed copy of a leaderboard computed from a finished run.