Codex – DeepSeek V4 Flash (high) vs. Codex – GPT-6.1 Sol (xhigh): geospatial agent comparison

Comparison between Codex – DeepSeek V4 Flash (high) 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 – DeepSeek V4 Flash (high) vs. Codex – GPT-6.1 Sol (xhigh)
Metric	Codex – DeepSeek V4 Flash (high)	Codex – GPT-6.1 Sol (xhigh)
Geospatial Agent Index	46* (partial: attempt 1 on 112 of 565 tasks)	72*
Earth-Bench V2 score	55	61
GeoBenchX score	37	69
GS-QA2 score	No data	86
GeoAgentBench score (guided GIS workflow; outside the index)	No data	100
GeoAnalystBench score (guided GIS workflow; outside the index)	No data	95
Raster and remote sensing score	54	75
Vector and overlay score	33	82
Networks and routing score	No data	No data
Climate and time series score	100	69
Spatial statistics and interpolation score	0	36
Mapping and cartography score	0	81
Recognising infeasible requests score	36	67
Cost per task	$0.034	$0.091
Time per task	8.9 min	2.2 min
Tokens per attempt	398k	154k
Turns per attempt	17.2	7.7
Attempts decided	65	565
Input price per 1M tokens	$0.44	$2.00
Output price per 1M tokens	$1.32	$10.00
Context window	1,048,576	No data
Image input	No	No data
Developer	DeepSeek	OpenAI

Charts

Partial coverage. Codex – DeepSeek V4 Flash (high): 11 of 147 Earth-Bench V2 tasks; 101 of 173 GeoBenchX tasks; GS-QA2 incomplete. Grey placeholders identify these entries in the index, cost and output token 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 (xhigh)	OpenAI	72*	No pending judgements; coverage incomplete; 211 results awaiting review	3 of 3	565 of 859 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. Codex – DeepSeek V4 Flash (high).

Data table: Cost per task

Cost per task
Model	Creator	Cost per task	Coverage (attempts)
Codex – GPT-6.1 Sol (xhigh)	OpenAI	$0.091	565 of 859 planned attempts

Output tokens per task

Average output tokens per attempt, reasoning included · Lower is better

Planned attempts still to come

How to read this chart

Not shown: partial coverage. Codex – DeepSeek V4 Flash (high).

Data table: Output tokens per task

Output tokens per task
Model	Creator	Output tokens per task	Coverage (attempts)
Codex – GPT-6.1 Sol (xhigh)	OpenAI	4k	565 of 859 planned attempts

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Codex – DeepSeek V4 Flash (high) or Codex – GPT-6.1 Sol (xhigh)?

Not comparable yet: Codex – DeepSeek V4 Flash (high) has partial coverage (11 of 147 Earth-Bench V2 tasks; 101 of 173 GeoBenchX tasks; GS-QA2 incomplete), so it is not ranked. Codex – DeepSeek V4 Flash (high): 65 of 614 planned attempts (97 excluded). Codex – GPT-6.1 Sol (xhigh): 565 of 859 planned attempts. Coverage is partial; scores can change as more attempts are decided.

Which is cheaper per task, Codex – DeepSeek V4 Flash (high) or Codex – GPT-6.1 Sol (xhigh)?

Codex – DeepSeek V4 Flash (high), at $0.034 against $0.091 for Codex – GPT-6.1 Sol (xhigh).

Which writes fewer output tokens per task, Codex – DeepSeek V4 Flash (high) or Codex – GPT-6.1 Sol (xhigh)?

Codex – GPT-6.1 Sol (xhigh), at 4k against 14k for Codex – DeepSeek V4 Flash (high).

Which has the larger context window, Codex – DeepSeek V4 Flash (high) or Codex – GPT-6.1 Sol (xhigh)?

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

More: Codex – DeepSeek V4 Flash (high) · Codex – GPT-6.1 Sol (xhigh) · all comparisons