Axis Spatial

Terminus-2 – Gemini 3.8 Flash (high) vs. Claude Code – Claude Opus 5.5 (high): geospatial agent comparison

Comparison between Terminus-2 – Gemini 3.8 Flash (high) and Claude Code – Claude Opus 5.5 (high) 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 3.8 Flash (high) vs. Claude Code – Claude Opus 5.5 (high)
MetricTerminus-2 – Gemini 3.8 Flash (high)Claude Code – Claude Opus 5.5 (high)
Geospatial Agent Index39* (attempts per task: 2.9)69* (attempts per task: 3.9)
GeoAgentBench score5893
GeoBenchX score4062
Earth-Bench score2821
GeoAnalystBench score32100
Raster and remote sensing score3756
Vector and overlay score4485
Networks and routing score80100
Climate and time series score2628
Spatial statistics and interpolation score1742
Mapping and cartography score2578
Recognising infeasible requests score6759
Cost per task$0.308$0.177
Time per task8.2 min1.0 min
Tokens per attempt982k135k
Turns per attempt32.46.0
Attempts decided278921
Input price per 1M tokens$0.75$4.00
Output price per 1M tokens$3.75$20.00
Context window1,048,576No data
Image inputYesNo data
DeveloperGoogleAnthropic

Charts

Geospatial Agent Index

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

  • Partial coverage
Geospatial Agent IndexClaude Code – Claude Opus 5.5 (high): 69* (partial coverage); Terminus-2 – Gemini 3.8 Flash (high): 39* (partial coverage)025507510069*Claude Opus 5.5 (high)39*Gemini 3.8 Flash (high)
Data table: Geospatial Agent Index
Geospatial Agent Index
ModelCreatorGeospatial Agent IndexRange while attempts are pendingBenchmarks coveredCoverage (attempts)
Claude Code – Claude Opus 5.5 (high)Anthropic69* (attempts per task: 3.9)66 to 804 of 4921 of 1,167 planned attempts
Terminus-2 – Gemini 3.8 Flash (high)Google39* (attempts per task: 2.9)13 to 804 of 4278 of 1,167 planned attempts (1 excluded)

Cost per task

Average cost per task (USD) · Lower is better

  • Partial coverage
Cost per taskClaude Code – Claude Opus 5.5 (high): $0.177 (partial coverage); Terminus-2 – Gemini 3.8 Flash (high): $0.308 (partial coverage)$0$0.100$0.200$0.300$0.400$0.177Claude Opus 5.5 (high)$0.308Gemini 3.8 Flash (high)
Data table: Cost per task
Cost per task
ModelCreatorCost per taskCoverage (attempts)
Terminus-2 – Gemini 3.8 Flash (high)Google$0.308835 of 1,167 planned attempts (1 excluded)
Claude Code – Claude Opus 5.5 (high)Anthropic$0.1771,132 of 1,167 planned attempts

Time per task

Average agent wall time per task · Lower is better

  • Partial coverage
Time per taskClaude Code – Claude Opus 5.5 (high): 1.0 min (partial coverage); Terminus-2 – Gemini 3.8 Flash (high): 8.2 min (partial coverage)0m2m4m6m8m1.0 minClaude Opus 5.5 (high)8.2 minGemini 3.8 Flash (high)
Data table: Time per task
Time per task
ModelCreatorTime per taskCoverage (attempts)
Terminus-2 – Gemini 3.8 Flash (high)Google8.2 min835 of 1,167 planned attempts (1 excluded)
Claude Code – Claude Opus 5.5 (high)Anthropic1.0 min1,132 of 1,167 planned attempts

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Terminus-2 – Gemini 3.8 Flash (high) or Claude Code – Claude Opus 5.5 (high)?
Claude Code – Claude Opus 5.5 (high), at 69 against 39 for Terminus-2 – Gemini 3.8 Flash (high). Terminus-2 – Gemini 3.8 Flash (high): 278 of 1,167 planned attempts (1 excluded). Claude Code – Claude Opus 5.5 (high): 921 of 1,167 planned attempts. Coverage is partial; scores can change as more attempts are decided.
Which is cheaper per task, Terminus-2 – Gemini 3.8 Flash (high) or Claude Code – Claude Opus 5.5 (high)?
Claude Code – Claude Opus 5.5 (high), at $0.177 against $0.308 for Terminus-2 – Gemini 3.8 Flash (high).
Which is faster per task, Terminus-2 – Gemini 3.8 Flash (high) or Claude Code – Claude Opus 5.5 (high)?
Claude Code – Claude Opus 5.5 (high), at 1.0 min against 8.2 min for Terminus-2 – Gemini 3.8 Flash (high).
Which has the larger context window, Terminus-2 – Gemini 3.8 Flash (high) or Claude Code – Claude Opus 5.5 (high)?
Not known yet: Claude Code – Claude Opus 5.5 (high) has no context window data.

More: Terminus-2 – Gemini 3.8 Flash (high) · Claude Code – Claude Opus 5.5 (high) · all comparisons