Axis Spatial

Terminus-2 – Gemini 3.1 Flash-Lite (minimal) vs. Codex – GPT-6.1 Sol (medium): geospatial agent comparison

Comparison between Terminus-2 – Gemini 3.1 Flash-Lite (minimal) and Codex – GPT-6.1 Sol (medium) 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 (minimal) vs. Codex – GPT-6.1 Sol (medium)
MetricTerminus-2 – Gemini 3.1 Flash-Lite (minimal)Codex – GPT-6.1 Sol (medium)
Geospatial Agent Index34* (attempts per task: 3)79* (attempts per task: 2.6)
GeoAgentBench score33100
GeoBenchX score4067
Earth-Bench score2851
GeoAnalystBench score37100
Raster and remote sensing score3071
Vector and overlay score2282
Networks and routing score0100
Climate and time series score4375
Spatial statistics and interpolation score1762
Mapping and cartography score3975
Recognising infeasible requests score5069
Cost per task$0.0056$0.060
Time per task0.5 min1.4 min
Tokens per attempt18k111k
Turns per attempt3.56.6
Attempts decided869749
Input price per 1M tokens$0.25$2.00
Output price per 1M tokens$1.50$10.00
Context window1,048,576No data
Image inputYesNo data
DeveloperGoogleOpenAI

Charts

Geospatial Agent Index

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

  • Partial coverage
Geospatial Agent IndexCodex – GPT-6.1 Sol (medium): 79* (partial coverage); Terminus-2 – Gemini 3.1 Flash-Lite (minimal): 34* (partial coverage)025507510079*GPT-6.1 Sol (medium)34*Gemini 3.1 Flash-Lite (minimal)
Data table: Geospatial Agent Index
Geospatial Agent Index
ModelCreatorGeospatial Agent IndexRange while attempts are pendingBenchmarks coveredCoverage (attempts)
Codex – GPT-6.1 Sol (medium)OpenAI79* (attempts per task: 2.6)No pending judgements; coverage incomplete4 of 4749 of 870 planned attempts (6 excluded)
Terminus-2 – Gemini 3.1 Flash-Lite (minimal)Google34* (attempts per task: 3)No pending judgements; coverage incomplete4 of 4869 of 870 planned attempts

Cost per task

Average cost per task (USD) · Lower is better

  • Partial coverage
Cost per taskTerminus-2 – Gemini 3.1 Flash-Lite (minimal): $0.0056 (partial coverage); Codex – GPT-6.1 Sol (medium): $0.060 (partial coverage)$0$0.020$0.040$0.060$0.080$0.0056Gemini 3.1 Flash-Lite (minimal)$0.060GPT-6.1 Sol (medium)
Data table: Cost per task
Cost per task
ModelCreatorCost per taskCoverage (attempts)
Terminus-2 – Gemini 3.1 Flash-Lite (minimal)Google$0.0056869 of 870 planned attempts
Codex – GPT-6.1 Sol (medium)OpenAI$0.060749 of 870 planned attempts (6 excluded)

Time per task

Average agent wall time per task · Lower is better

  • Partial coverage
Time per taskTerminus-2 – Gemini 3.1 Flash-Lite (minimal): 0.5 min (partial coverage); Codex – GPT-6.1 Sol (medium): 1.4 min (partial coverage)0m0m1m1m2m0.5 minGemini 3.1 Flash-Lite (minimal)1.4 minGPT-6.1 Sol (medium)
Data table: Time per task
Time per task
ModelCreatorTime per taskCoverage (attempts)
Terminus-2 – Gemini 3.1 Flash-Lite (minimal)Google0.5 min869 of 870 planned attempts
Codex – GPT-6.1 Sol (medium)OpenAI1.4 min749 of 870 planned attempts (6 excluded)

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Terminus-2 – Gemini 3.1 Flash-Lite (minimal) or Codex – GPT-6.1 Sol (medium)?
Codex – GPT-6.1 Sol (medium), at 79 against 34 for Terminus-2 – Gemini 3.1 Flash-Lite (minimal). Terminus-2 – Gemini 3.1 Flash-Lite (minimal): 869 of 870 planned attempts. Codex – GPT-6.1 Sol (medium): 749 of 870 planned attempts (6 excluded). Coverage is partial; scores can change as more attempts are decided.
Which is cheaper per task, Terminus-2 – Gemini 3.1 Flash-Lite (minimal) or Codex – GPT-6.1 Sol (medium)?
Terminus-2 – Gemini 3.1 Flash-Lite (minimal), at $0.0056 against $0.060 for Codex – GPT-6.1 Sol (medium).
Which is faster per task, Terminus-2 – Gemini 3.1 Flash-Lite (minimal) or Codex – GPT-6.1 Sol (medium)?
Terminus-2 – Gemini 3.1 Flash-Lite (minimal), at 0.5 min against 1.4 min for Codex – GPT-6.1 Sol (medium).
Which has the larger context window, Terminus-2 – Gemini 3.1 Flash-Lite (minimal) or Codex – GPT-6.1 Sol (medium)?
Not known yet: Codex – GPT-6.1 Sol (medium) has no context window data.

More: Terminus-2 – Gemini 3.1 Flash-Lite (minimal) · Codex – GPT-6.1 Sol (medium) · all comparisons