Codex – DeepSeek V4 Pro (high) vs. Codex – GPT-5.6 Luna (low): geospatial agent comparison

Comparison between Codex – DeepSeek V4 Pro (high) and Codex – GPT-5.6 Luna (low) 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 Pro (high) vs. Codex – GPT-5.6 Luna (low)
Metric	Codex – DeepSeek V4 Pro (high)	Codex – GPT-5.6 Luna (low)
Geospatial Agent Index	62* (partial: attempt 1 on 116 of 488 tasks)	60* (partial: attempt 1 on 397 of 488 tasks)
Earth-Bench V2 score	57	44
GeoBenchX score	66	61
GS-QA2 score	No data	76
GeoAgentBench score (guided GIS workflow; outside the index)	No data	86
GeoAnalystBench score (guided GIS workflow; outside the index)	No data	95
Raster and remote sensing score	62	70
Vector and overlay score	0	72
Climate and time series score	42	42
Spatial statistics and interpolation score	17	0
Mapping and cartography score	85	83
Recognising infeasible requests score	65	50
Cost per task	$0.64	$0.0057
Time per task	10.3 min	1.6 min
Tokens per attempt	828k	84k
Turns per attempt	20.8	7.1
Attempts decided	116	397
Input price per 1M tokens	$1.32	$0.20
Output price per 1M tokens	$3.96	$1.20
Context window	1,048,576	No data
Image input	No	No data
Developer	DeepSeek	OpenAI

Charts

Partial coverage. Codex – DeepSeek V4 Pro (high): 28 of 117 Earth-Bench V2 tasks; 88 of 150 GeoBenchX tasks; GS-QA2 incomplete; Codex – GPT-5.6 Luna (low): 59 of 150 GeoBenchX tasks. 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

Data table: Geospatial Agent Index

Geospatial Agent Index
Model	Creator	Geospatial Agent Index	Range while attempts are pending	Benchmarks covered	Coverage (attempts)

Cost per task

Average cost per task (USD) · Lower is better

How to read this chart

Not shown: partial coverage. 2 entries without a first attempt on every index task. What is still running is on the models page.

Data table: Cost per task

Cost per task
Model	Creator	Cost per task	Coverage (attempts)

Output tokens per task

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

How to read this chart

Not shown: partial coverage. 2 entries without a first attempt on every index task. What is still running is on the models page.

Data table: Output tokens per task

Output tokens per task
Model	Creator	Output tokens per task	Coverage (attempts)

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Codex – DeepSeek V4 Pro (high) or Codex – GPT-5.6 Luna (low)?

Not comparable yet: Codex – DeepSeek V4 Pro (high) has partial coverage (28 of 117 Earth-Bench V2 tasks; 88 of 150 GeoBenchX tasks; GS-QA2 incomplete) and Codex – GPT-5.6 Luna (low) has partial coverage (59 of 150 GeoBenchX tasks), so it is not ranked. Codex – DeepSeek V4 Pro (high): 116 of 501 scheduled attempts (109 excluded). Codex – GPT-5.6 Luna (low): 397 of 722 scheduled attempts. Coverage is partial; scores can change as more attempts are decided.

Which is cheaper per task, Codex – DeepSeek V4 Pro (high) or Codex – GPT-5.6 Luna (low)?

Codex – GPT-5.6 Luna (low), at $0.0057 against $0.64 for Codex – DeepSeek V4 Pro (high).

Which writes fewer output tokens per task, Codex – DeepSeek V4 Pro (high) or Codex – GPT-5.6 Luna (low)?

Codex – GPT-5.6 Luna (low), at 1k against 16k for Codex – DeepSeek V4 Pro (high).

Which has the larger context window, Codex – DeepSeek V4 Pro (high) or Codex – GPT-5.6 Luna (low)?

Not known yet: Codex – GPT-5.6 Luna (low) has no context window data.

More: Codex – DeepSeek V4 Pro (high) · Codex – GPT-5.6 Luna (low) · all comparisons