Axis Spatial

Terminus-2 – Gemini 3.1 Flash-Lite (high) vs. Terminus-2 – Gemma 4 26B A4B (thinking on): geospatial agent comparison

Comparison between Terminus-2 – Gemini 3.1 Flash-Lite (high) 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 Flash-Lite (high) vs. Terminus-2 – Gemma 4 26B A4B (thinking on)
MetricTerminus-2 – Gemini 3.1 Flash-Lite (high)Terminus-2 – Gemma 4 26B A4B (thinking on)
Geospatial Agent Index59* (attempts per task: 3)62 (attempts per task: 3)
GeoAgentBench score6987
GeoBenchX score5353
Earth-Bench score4334
GeoAnalystBench score7072
Raster and remote sensing score5457
Vector and overlay score6574
Networks and routing score6087
Climate and time series score5750
Spatial statistics and interpolation score4657
Mapping and cartography score6671
Recognising infeasible requests score4843
Cost per task$0.021$0.016
Time per task1.9 min7.0 min
Tokens per attempt52k127k
Turns per attempt5.99.9
Attempts decided864870
Input price per 1M tokens$0.25$0.10
Output price per 1M tokens$1.50$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

  • Partial coverage
Geospatial Agent IndexTerminus-2 – Gemma 4 26B A4B (thinking on): 62; Terminus-2 – Gemini 3.1 Flash-Lite (high): 59* (partial coverage)025507510062Gemma 4 26B A4B (thinking on)59*Gemini 3.1 Flash-Lite (high)
Data table: Geospatial Agent Index
Geospatial Agent Index
ModelCreatorGeospatial Agent IndexRange while attempts are pendingBenchmarks coveredCoverage (attempts)
Terminus-2 – Gemma 4 26B A4B (thinking on)Google62 (attempts per task: 3)No pending judgements4 of 4870 of 870 planned attempts
Terminus-2 – Gemini 3.1 Flash-Lite (high)Google59* (attempts per task: 3)59 to 594 of 4864 of 870 planned attempts (6 excluded)

Cost per task

Average cost per task (USD) · Lower is better

  • Partial coverage
Cost per taskTerminus-2 – Gemma 4 26B A4B (thinking on): $0.016; Terminus-2 – Gemini 3.1 Flash-Lite (high): $0.021 (partial coverage)$0$0.0063$0.013$0.019$0.025$0.016Gemma 4 26B A4B (thinking on)$0.021Gemini 3.1 Flash-Lite (high)
Data table: Cost per task
Cost per task
ModelCreatorCost per taskCoverage (attempts)
Terminus-2 – Gemini 3.1 Flash-Lite (high)Google$0.021865 of 870 planned attempts (6 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

  • Partial coverage
Time per taskTerminus-2 – Gemini 3.1 Flash-Lite (high): 1.9 min (partial coverage); Terminus-2 – Gemma 4 26B A4B (thinking on): 7.0 min0m2m4m6m8m1.9 minGemini 3.1 Flash-Lite (high)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 Flash-Lite (high)Google1.9 min865 of 870 planned attempts (6 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 Flash-Lite (high) or Terminus-2 – Gemma 4 26B A4B (thinking on)?
Terminus-2 – Gemma 4 26B A4B (thinking on), at 62 against 59 for Terminus-2 – Gemini 3.1 Flash-Lite (high). Terminus-2 – Gemini 3.1 Flash-Lite (high): 864 of 870 planned attempts (6 excluded). Terminus-2 – Gemma 4 26B A4B (thinking on): 870 of 870 planned attempts. Coverage is partial; scores can change as more attempts are decided.
Which is cheaper per task, Terminus-2 – Gemini 3.1 Flash-Lite (high) or Terminus-2 – Gemma 4 26B A4B (thinking on)?
Terminus-2 – Gemma 4 26B A4B (thinking on), at $0.016 against $0.021 for Terminus-2 – Gemini 3.1 Flash-Lite (high).
Which is faster per task, Terminus-2 – Gemini 3.1 Flash-Lite (high) or Terminus-2 – Gemma 4 26B A4B (thinking on)?
Terminus-2 – Gemini 3.1 Flash-Lite (high), at 1.9 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 Flash-Lite (high) or Terminus-2 – Gemma 4 26B A4B (thinking on)?
Terminus-2 – Gemini 3.1 Flash-Lite (high), at 1,048,576 tokens against 256,000 tokens for Terminus-2 – Gemma 4 26B A4B (thinking on).

More: Terminus-2 – Gemini 3.1 Flash-Lite (high) · Terminus-2 – Gemma 4 26B A4B (thinking on) · all comparisons