Axis Spatial

Terminus-2 – Gemini 3.1 Pro (preview) (low) vs. Terminus-2 – Gemma 4 26B A4B (thinking on): geospatial agent comparison

Comparison between Terminus-2 – Gemini 3.1 Pro (preview) (low) and Terminus-2 – Gemma 4 26B A4B (thinking on) 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 – Gemini 3.1 Pro (preview) (low) vs. Terminus-2 – Gemma 4 26B A4B (thinking on)
MetricTerminus-2 – Gemini 3.1 Pro (preview) (low)Terminus-2 – Gemma 4 26B A4B (thinking on)
Geospatial Agent Index65 (attempts per task: 3)62 (attempts per task: 3)
GeoAgentBench score8387
GeoBenchX score6153
Earth-Bench score4234
GeoAnalystBench score7572
Raster and remote sensing score5857
Vector and overlay score6974
Networks and routing score9387
Climate and time series score6750
Spatial statistics and interpolation score5157
Mapping and cartography score5571
Recognising infeasible requests score7143
Cost per task$0.061$0.016
Time per task1.0 min7.0 min
Tokens per attempt19k127k
Turns per attempt3.89.9
Attempts decided870870
Input price per 1M tokens$2.00$0.10
Output price per 1M tokens$12.00$0.30
Context window1,048,576256,000
Image inputYesYes
DeveloperGoogleGoogle

Charts

Geospatial Agent Index

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

Geospatial Agent IndexTerminus-2 – Gemini 3.1 Pro (preview) (low): 65; Terminus-2 – Gemma 4 26B A4B (thinking on): 62025507510065Gemini 3.1 Pro (preview) (low)62Gemma 4 26B A4B (thinking on)
Data table: Geospatial Agent Index
Geospatial Agent Index
ModelCreatorGeospatial Agent IndexRange while attempts are pendingBenchmarks coveredCoverage (attempts)
Terminus-2 – Gemini 3.1 Pro (preview) (low)Google65 (attempts per task: 3)No pending judgements4 of 4870 of 870 planned attempts (22 excluded)
Terminus-2 – Gemma 4 26B A4B (thinking on)Google62 (attempts per task: 3)No pending judgements4 of 4870 of 870 planned attempts

Cost per task

Average cost per task (USD) · Lower is better

Cost per taskTerminus-2 – Gemma 4 26B A4B (thinking on): $0.016; Terminus-2 – Gemini 3.1 Pro (preview) (low): $0.061$0$0.020$0.040$0.060$0.080$0.016Gemma 4 26B A4B (thinking on)$0.061Gemini 3.1 Pro (preview) (low)
Data table: Cost per task
Cost per task
ModelCreatorCost per taskCoverage (attempts)
Terminus-2 – Gemini 3.1 Pro (preview) (low)Google$0.061870 of 870 planned attempts (22 excluded)
Terminus-2 – Gemma 4 26B A4B (thinking on)Google$0.016870 of 870 planned attempts

Time per task

Average agent wall time per task · Lower is better

Time per taskTerminus-2 – Gemini 3.1 Pro (preview) (low): 1.0 min; Terminus-2 – Gemma 4 26B A4B (thinking on): 7.0 min0m2m4m6m8m1.0 minGemini 3.1 Pro (preview) (low)7.0 minGemma 4 26B A4B (thinking on)
Data table: Time per task
Time per task
ModelCreatorTime per taskCoverage (attempts)
Terminus-2 – Gemini 3.1 Pro (preview) (low)Google1.0 min870 of 870 planned attempts (22 excluded)
Terminus-2 – Gemma 4 26B A4B (thinking on)Google7.0 min870 of 870 planned attempts

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Terminus-2 – Gemini 3.1 Pro (preview) (low) or Terminus-2 – Gemma 4 26B A4B (thinking on)?
Terminus-2 – Gemini 3.1 Pro (preview) (low), at 65 against 62 for Terminus-2 – Gemma 4 26B A4B (thinking on). Terminus-2 – Gemini 3.1 Pro (preview) (low): 870 of 870 planned attempts (22 excluded). Terminus-2 – Gemma 4 26B A4B (thinking on): 870 of 870 planned attempts.
Which is cheaper per task, Terminus-2 – Gemini 3.1 Pro (preview) (low) or Terminus-2 – Gemma 4 26B A4B (thinking on)?
Terminus-2 – Gemma 4 26B A4B (thinking on), at $0.016 against $0.061 for Terminus-2 – Gemini 3.1 Pro (preview) (low).
Which is faster per task, Terminus-2 – Gemini 3.1 Pro (preview) (low) or Terminus-2 – Gemma 4 26B A4B (thinking on)?
Terminus-2 – Gemini 3.1 Pro (preview) (low), at 1.0 min against 7.0 min for Terminus-2 – Gemma 4 26B A4B (thinking on).
Which has the larger context window, Terminus-2 – Gemini 3.1 Pro (preview) (low) or Terminus-2 – Gemma 4 26B A4B (thinking on)?
Terminus-2 – Gemini 3.1 Pro (preview) (low), at 1,048,576 tokens against 256,000 tokens for Terminus-2 – Gemma 4 26B A4B (thinking on).

More: Terminus-2 – Gemini 3.1 Pro (preview) (low) · Terminus-2 – Gemma 4 26B A4B (thinking on) · all comparisons