Axis Spatial

Codex – GPT-6.1 Sol (medium) vs. Codex – GPT-6.1 Sol (xhigh): geospatial agent comparison

Comparison between Codex – GPT-6.1 Sol (medium) and Codex – GPT-6.1 Sol (xhigh) on the Geospatial Agent Index, each benchmark, cost, time and token use, from the same tasks, agent and limits. Methodology.

Side by side

Codex – GPT-6.1 Sol (medium) vs. Codex – GPT-6.1 Sol (xhigh)
MetricCodex – GPT-6.1 Sol (medium)Codex – GPT-6.1 Sol (xhigh)
Geospatial Agent Index79* (partial: 2.6 of 3 attempts)78* (partial: 2 of 3 attempts)
GeoAgentBench score100100
GeoBenchX score6764
Earth-Bench score5148
GeoAnalystBench score100100
Raster and remote sensing score7170
Vector and overlay score8278
Networks and routing score100100
Climate and time series score7572
Spatial statistics and interpolation score6262
Mapping and cartography score7573
Recognising infeasible requests score6966
Cost per task$0.060$0.124
Time per task1.4 min3.0 min
Tokens per attempt111k201k
Turns per attempt6.69.0
Attempts decided749551
Input price per 1M tokens$2.00$2.00
Output price per 1M tokens$10.00$10.00
Context windowNo dataNo data
Image inputNo dataNo data
DeveloperOpenAIOpenAI

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); Codex – GPT-6.1 Sol (xhigh): 78* (partial coverage)025507510079*GPT-6.1 Sol (medium)78*GPT-6.1 Sol (xhigh)
Data table: Geospatial Agent Index
Geospatial Agent Index
ModelCreatorGeospatial Agent IndexRange while attempts are pendingBenchmarks coveredCoverage (attempts)
Codex – GPT-6.1 Sol (medium)OpenAI79* (partial: 2.6 of 3 attempts)No pending judgements; coverage incomplete4 of 4749 of 870 planned attempts (6 excluded)
Codex – GPT-6.1 Sol (xhigh)OpenAI78* (partial: 2 of 3 attempts)74 to 794 of 4551 of 870 planned attempts

Cost per task

Average cost per task (USD) · Lower is better

  • Partial coverage
Cost per taskCodex – GPT-6.1 Sol (medium): $0.060 (partial coverage); Codex – GPT-6.1 Sol (xhigh): $0.124 (partial coverage)$0$0.038$0.075$0.113$0.150$0.060GPT-6.1 Sol (medium)$0.124GPT-6.1 Sol (xhigh)
Data table: Cost per task
Cost per task
ModelCreatorCost per taskCoverage (attempts)
Codex – GPT-6.1 Sol (medium)OpenAI$0.060749 of 870 planned attempts (6 excluded)
Codex – GPT-6.1 Sol (xhigh)OpenAI$0.124591 of 870 planned attempts

Time per task

Average agent wall time per task · Lower is better

  • Partial coverage
Time per taskCodex – GPT-6.1 Sol (medium): 1.4 min (partial coverage); Codex – GPT-6.1 Sol (xhigh): 3.0 min (partial coverage)0m1m2m2m3m1.4 minGPT-6.1 Sol (medium)3.0 minGPT-6.1 Sol (xhigh)
Data table: Time per task
Time per task
ModelCreatorTime per taskCoverage (attempts)
Codex – GPT-6.1 Sol (medium)OpenAI1.4 min749 of 870 planned attempts (6 excluded)
Codex – GPT-6.1 Sol (xhigh)OpenAI3.0 min591 of 870 planned attempts

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Codex – GPT-6.1 Sol (medium) or Codex – GPT-6.1 Sol (xhigh)?
Codex – GPT-6.1 Sol (medium), at 79 against 78 for Codex – GPT-6.1 Sol (xhigh). Codex – GPT-6.1 Sol (medium): 749 of 870 planned attempts (6 excluded). Codex – GPT-6.1 Sol (xhigh): 551 of 870 planned attempts. Coverage is partial; scores can change as more attempts are decided.
Which is cheaper per task, Codex – GPT-6.1 Sol (medium) or Codex – GPT-6.1 Sol (xhigh)?
Codex – GPT-6.1 Sol (medium), at $0.060 against $0.124 for Codex – GPT-6.1 Sol (xhigh).
Which is faster per task, Codex – GPT-6.1 Sol (medium) or Codex – GPT-6.1 Sol (xhigh)?
Codex – GPT-6.1 Sol (medium), at 1.4 min against 3.0 min for Codex – GPT-6.1 Sol (xhigh).
Which has the larger context window, Codex – GPT-6.1 Sol (medium) or Codex – GPT-6.1 Sol (xhigh)?
Not known yet: Codex – GPT-6.1 Sol (medium) has no context window data and Codex – GPT-6.1 Sol (xhigh) has no context window data.

More: Codex – GPT-6.1 Sol (medium) · Codex – GPT-6.1 Sol (xhigh) · all comparisons