Axis Spatial

Terminus-2 – Gemma 4 26B A4B (thinking on) vs. Terminus-2 – Kimi K3 (always on): geospatial agent comparison

Comparison between Terminus-2 – Gemma 4 26B A4B (thinking on) and Terminus-2 – Kimi K3 (always 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 – Gemma 4 26B A4B (thinking on) vs. Terminus-2 – Kimi K3 (always on)
MetricTerminus-2 – Gemma 4 26B A4B (thinking on)Terminus-2 – Kimi K3 (always on)
Geospatial Agent Index39*58*
Earth-Bench V2 score2961
GeoBenchX score4955
GeoAgentBench score (guided GIS workflow; outside the index)8294
GeoAnalystBench score (guided GIS workflow; outside the index)6389
Raster and remote sensing score3159
Vector and overlay score6733
Networks and routing scoreNo dataNo data
Climate and time series score3466
Spatial statistics and interpolation score750
Mapping and cartography score5678
Recognising infeasible requests score4738
Cost per task$0.018$0.336
Time per task10.9 min3.9 min
Tokens per attempt140k76k
Turns per attempt10.37.7
Attempts decided320320
Input price per 1M tokens$0.10$3.00
Output price per 1M tokens$0.30$15.00
Context window256,0001,000,000
Image inputYesYes
DeveloperGoogleMoonshot AI

Charts

Geospatial Agent Index

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

  • Planned attempts still to come
Geospatial Agent IndexTerminus-2 – Kimi K3 (always on): 58* (partial coverage); Terminus-2 – Gemma 4 26B A4B (thinking on): 39* (partial coverage)025507510058*Kimi K3 (always on)39*Gemma 4 26B A4B (thinking on)
Data table: Geospatial Agent Index
Geospatial Agent Index
ModelCreatorGeospatial Agent IndexRange while attempts are pendingBenchmarks coveredCoverage (attempts)
Terminus-2 – Kimi K3 (always on)Moonshot AI58*No pending judgements; coverage incomplete; 1 trace review declined by the judge2 of 2320 of 614 planned attempts
Terminus-2 – Gemma 4 26B A4B (thinking on)Google39*No pending judgements; coverage incomplete2 of 2320 of 614 planned attempts

Cost per task

Average cost per task (USD) · Lower is better

  • Planned attempts still to come
Cost per taskTerminus-2 – Gemma 4 26B A4B (thinking on): $0.018 (partial coverage); Terminus-2 – Kimi K3 (always on): $0.336 (partial coverage)$0$0.100$0.200$0.300$0.400$0.018Gemma 4 26B A4B (thinking on)$0.336Kimi K3 (always on)
Data table: Cost per task
Cost per task
ModelCreatorCost per taskCoverage (attempts)
Terminus-2 – Gemma 4 26B A4B (thinking on)Google$0.018320 of 614 planned attempts
Terminus-2 – Kimi K3 (always on)Moonshot AI$0.336320 of 614 planned attempts

Time per task

Average agent wall time per task · Lower is better

  • Planned attempts still to come
Time per taskTerminus-2 – Kimi K3 (always on): 3.9 min (partial coverage); Terminus-2 – Gemma 4 26B A4B (thinking on): 10.9 min (partial coverage)0m3m7m10m13m3.9 minKimi K3 (always on)10.9 minGemma 4 26B A4B (thinking on)
Data table: Time per task
Time per task
ModelCreatorTime per taskCoverage (attempts)
Terminus-2 – Gemma 4 26B A4B (thinking on)Google10.9 min320 of 614 planned attempts
Terminus-2 – Kimi K3 (always on)Moonshot AI3.9 min320 of 614 planned attempts

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Terminus-2 – Gemma 4 26B A4B (thinking on) or Terminus-2 – Kimi K3 (always on)?
Terminus-2 – Kimi K3 (always on), at 58 against 39 for Terminus-2 – Gemma 4 26B A4B (thinking on). Terminus-2 – Gemma 4 26B A4B (thinking on): 320 of 614 planned attempts. Terminus-2 – Kimi K3 (always on): 320 of 614 planned attempts. Coverage is partial; scores can change as more attempts are decided.
Which is cheaper per task, Terminus-2 – Gemma 4 26B A4B (thinking on) or Terminus-2 – Kimi K3 (always on)?
Terminus-2 – Gemma 4 26B A4B (thinking on), at $0.018 against $0.336 for Terminus-2 – Kimi K3 (always on).
Which is faster per task, Terminus-2 – Gemma 4 26B A4B (thinking on) or Terminus-2 – Kimi K3 (always on)?
Terminus-2 – Kimi K3 (always on), at 3.9 min against 10.9 min for Terminus-2 – Gemma 4 26B A4B (thinking on).
Which has the larger context window, Terminus-2 – Gemma 4 26B A4B (thinking on) or Terminus-2 – Kimi K3 (always on)?
Terminus-2 – Kimi K3 (always on), at 1,000,000 tokens against 256,000 tokens for Terminus-2 – Gemma 4 26B A4B (thinking on).

More: Terminus-2 – Gemma 4 26B A4B (thinking on) · Terminus-2 – Kimi K3 (always on) · all comparisons