Axis Spatial

Terminus-2 – Gemini 3.1 Pro (preview) (high) vs. Terminus-2 – Kimi K2.7 Code (always on): geospatial agent comparison

Comparison between Terminus-2 – Gemini 3.1 Pro (preview) (high) and Terminus-2 – Kimi K2.7 Code (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 – Gemini 3.1 Pro (preview) (high) vs. Terminus-2 – Kimi K2.7 Code (always on)
MetricTerminus-2 – Gemini 3.1 Pro (preview) (high)Terminus-2 – Kimi K2.7 Code (always on)
Geospatial Agent Index75 (attempts per task: 3)74 (attempts per task: 3)
GeoAgentBench score9491
GeoBenchX score6554
Earth-Bench score5462
GeoAnalystBench score8688
Raster and remote sensing score6774
Vector and overlay score7878
Networks and routing score9387
Climate and time series score8278
Spatial statistics and interpolation score7260
Mapping and cartography score5772
Recognising infeasible requests score7541
Cost per task$0.252$0.119
Time per task3.4 min6.5 min
Tokens per attempt73k290k
Turns per attempt7.114.1
Attempts decided870870
Input price per 1M tokens$2.00$0.95
Output price per 1M tokens$12.00$4.00
Context window1,048,576262,144
Image inputYesYes
DeveloperGoogleMoonshot AI

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) (high): 75; Terminus-2 – Kimi K2.7 Code (always on): 74025507510075Gemini 3.1 Pro (preview) (high)74Kimi K2.7 Code (always 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) (high)Google75 (attempts per task: 3)No pending judgements4 of 4870 of 870 planned attempts
Terminus-2 – Kimi K2.7 Code (always on)Moonshot AI74 (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 – Kimi K2.7 Code (always on): $0.119; Terminus-2 – Gemini 3.1 Pro (preview) (high): $0.252$0$0.075$0.150$0.225$0.300$0.119Kimi K2.7 Code (always on)$0.252Gemini 3.1 Pro (preview) (high)
Data table: Cost per task
Cost per task
ModelCreatorCost per taskCoverage (attempts)
Terminus-2 – Gemini 3.1 Pro (preview) (high)Google$0.252870 of 870 planned attempts
Terminus-2 – Kimi K2.7 Code (always on)Moonshot AI$0.119870 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) (high): 3.4 min; Terminus-2 – Kimi K2.7 Code (always on): 6.5 min0m2m3m5m7m3.4 minGemini 3.1 Pro (preview) (high)6.5 minKimi K2.7 Code (always on)
Data table: Time per task
Time per task
ModelCreatorTime per taskCoverage (attempts)
Terminus-2 – Gemini 3.1 Pro (preview) (high)Google3.4 min870 of 870 planned attempts
Terminus-2 – Kimi K2.7 Code (always on)Moonshot AI6.5 min870 of 870 planned attempts

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Terminus-2 – Gemini 3.1 Pro (preview) (high) or Terminus-2 – Kimi K2.7 Code (always on)?
Terminus-2 – Gemini 3.1 Pro (preview) (high), at 75 against 74 for Terminus-2 – Kimi K2.7 Code (always on). Terminus-2 – Gemini 3.1 Pro (preview) (high): 870 of 870 planned attempts. Terminus-2 – Kimi K2.7 Code (always on): 870 of 870 planned attempts.
Which is cheaper per task, Terminus-2 – Gemini 3.1 Pro (preview) (high) or Terminus-2 – Kimi K2.7 Code (always on)?
Terminus-2 – Kimi K2.7 Code (always on), at $0.119 against $0.252 for Terminus-2 – Gemini 3.1 Pro (preview) (high).
Which is faster per task, Terminus-2 – Gemini 3.1 Pro (preview) (high) or Terminus-2 – Kimi K2.7 Code (always on)?
Terminus-2 – Gemini 3.1 Pro (preview) (high), at 3.4 min against 6.5 min for Terminus-2 – Kimi K2.7 Code (always on).
Which has the larger context window, Terminus-2 – Gemini 3.1 Pro (preview) (high) or Terminus-2 – Kimi K2.7 Code (always on)?
Terminus-2 – Gemini 3.1 Pro (preview) (high), at 1,048,576 tokens against 262,144 tokens for Terminus-2 – Kimi K2.7 Code (always on).

More: Terminus-2 – Gemini 3.1 Pro (preview) (high) · Terminus-2 – Kimi K2.7 Code (always on) · all comparisons