Kimi Code – Kimi K2.7 Code (always on) vs. Codex – GPT-6.1 Sol (medium): geospatial agent comparison

Comparison between Kimi Code – Kimi K2.7 Code (always on) 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

Kimi Code – Kimi K2.7 Code (always on) vs. Codex – GPT-6.1 Sol (medium)
Metric	Kimi Code – Kimi K2.7 Code (always on)	Codex – GPT-6.1 Sol (medium)
Geospatial Agent Index	54* (partial: attempt 1 on 82 of 320 tasks)	65*
Earth-Bench V2 score	58	61
GeoBenchX score	49	69
GeoAgentBench score (guided GIS workflow; outside the index)	No data	100
GeoAnalystBench score (guided GIS workflow; outside the index)	No data	100
Raster and remote sensing score	67	59
Vector and overlay score	0	67
Networks and routing score	No data	No data
Climate and time series score	0	68
Spatial statistics and interpolation score	17	29
Mapping and cartography score	81	78
Recognising infeasible requests score	31	70
Cost per task	$0.227	$0.061
Time per task	8.3 min	1.4 min
Tokens per attempt	802k	112k
Turns per attempt	No data	6.5
Attempts decided	79	320
Input price per 1M tokens	$0.95	$2.00
Output price per 1M tokens	$4.00	$10.00
Context window	262,144	No data
Image input	Yes	No data
Developer	Moonshot AI	OpenAI

Charts

Partial coverage. Kimi Code – Kimi K2.7 Code (always on): 12 of 147 Earth-Bench V2 tasks; 70 of 173 GeoBenchX tasks. Grey placeholders identify these entries in the index, cost and time charts; their height does not represent a value. Comparable bars appear when first-attempt coverage is complete. Their available results remain in the side-by-side table.

Geospatial Agent Index

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

Planned attempts still to come

Data table: Geospatial Agent Index

Geospatial Agent Index
Model	Creator	Geospatial Agent Index	Range while attempts are pending	Benchmarks covered	Coverage (attempts)
Codex – GPT-6.1 Sol (medium)	OpenAI	65*	No pending judgements; coverage incomplete	2 of 2	320 of 614 planned attempts

Cost per task

Average cost per task (USD) · Lower is better

Planned attempts still to come

How to read this chart

Not shown: partial coverage. Kimi Code – Kimi K2.7 Code (always on).

Data table: Cost per task

Cost per task
Model	Creator	Cost per task	Coverage (attempts)
Codex – GPT-6.1 Sol (medium)	OpenAI	$0.061	320 of 614 planned attempts

Time per task

Average agent wall time per task · Lower is better

Planned attempts still to come

How to read this chart

Not shown: partial coverage. Kimi Code – Kimi K2.7 Code (always on).

Data table: Time per task

Time per task
Model	Creator	Time per task	Coverage (attempts)
Codex – GPT-6.1 Sol (medium)	OpenAI	1.4 min	320 of 614 planned attempts

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Kimi Code – Kimi K2.7 Code (always on) or Codex – GPT-6.1 Sol (medium)?

Not comparable yet: Kimi Code – Kimi K2.7 Code (always on) has partial coverage (12 of 147 Earth-Bench V2 tasks; 70 of 173 GeoBenchX tasks), so it is not ranked. Kimi Code – Kimi K2.7 Code (always on): 79 of 614 planned attempts. Codex – GPT-6.1 Sol (medium): 320 of 614 planned attempts. Coverage is partial; scores can change as more attempts are decided.

Which is cheaper per task, Kimi Code – Kimi K2.7 Code (always on) or Codex – GPT-6.1 Sol (medium)?

Codex – GPT-6.1 Sol (medium), at $0.061 against $0.227 for Kimi Code – Kimi K2.7 Code (always on).

Which is faster per task, Kimi Code – Kimi K2.7 Code (always on) or Codex – GPT-6.1 Sol (medium)?

Codex – GPT-6.1 Sol (medium), at 1.4 min against 8.3 min for Kimi Code – Kimi K2.7 Code (always on).

Which has the larger context window, Kimi Code – Kimi K2.7 Code (always on) or Codex – GPT-6.1 Sol (medium)?

Not known yet: Codex – GPT-6.1 Sol (medium) has no context window data.

More: Kimi Code – Kimi K2.7 Code (always on) · Codex – GPT-6.1 Sol (medium) · all comparisons