Terminus-2 – DeepSeek V4 Pro (high) vs. Codex – GPT-6 Luna (high): geospatial agent comparison

Comparison between Terminus-2 – DeepSeek V4 Pro (high) and Codex – GPT-6 Luna (high) 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 – DeepSeek V4 Pro (high) vs. Codex – GPT-6 Luna (high)
Metric	Terminus-2 – DeepSeek V4 Pro (high)	Codex – GPT-6 Luna (high)
Geospatial Agent Index	71* (partial: attempt 1 on 483 of 488 tasks)	71* (partial: attempt 1 on 444 of 488 tasks)
Earth-Bench V2 score	68	66
GeoBenchX score	65	71
GS-QA2 score	78	77
GeoAgentBench score (guided GIS workflow; outside the index)	96	96
GeoAnalystBench score (guided GIS workflow; outside the index)	100	100
Raster and remote sensing score	79	73
Vector and overlay score	74	77
Climate and time series score	66	69
Spatial statistics and interpolation score	23	33
Mapping and cartography score	81	71
Recognising infeasible requests score	62	78
Cost per task	$0.29	$0.0039
Time per task	7.3 min	1.7 min
Tokens per attempt	232k	116k
Turns per attempt	13.6	7.3
Attempts decided	483	430
Input price per 1M tokens	$1.32	$0.10
Output price per 1M tokens	$3.96	$0.50
Context window	1,048,576	No data
Image input	No	No data
Developer	DeepSeek	OpenAI

Charts

Partial coverage. Terminus-2 – DeepSeek V4 Pro (high): 216 of 221 GS-QA2 tasks; Codex – GPT-6 Luna (high): 106 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, Terminus-2 – DeepSeek V4 Pro (high) or Codex – GPT-6 Luna (high)?

Not comparable yet: Terminus-2 – DeepSeek V4 Pro (high) has partial coverage (216 of 221 GS-QA2 tasks) and Codex – GPT-6 Luna (high) has partial coverage (106 of 150 GeoBenchX tasks), so it is not ranked. Terminus-2 – DeepSeek V4 Pro (high): 483 of 722 scheduled attempts. Codex – GPT-6 Luna (high): 430 of 722 scheduled attempts. Coverage is partial; scores can change as more attempts are decided.

Which is cheaper per task, Terminus-2 – DeepSeek V4 Pro (high) or Codex – GPT-6 Luna (high)?

Codex – GPT-6 Luna (high), at $0.0039 against $0.29 for Terminus-2 – DeepSeek V4 Pro (high).

Which writes fewer output tokens per task, Terminus-2 – DeepSeek V4 Pro (high) or Codex – GPT-6 Luna (high)?

Codex – GPT-6 Luna (high), at 3k against 19k for Terminus-2 – DeepSeek V4 Pro (high).

Which has the larger context window, Terminus-2 – DeepSeek V4 Pro (high) or Codex – GPT-6 Luna (high)?

Not known yet: Codex – GPT-6 Luna (high) has no context window data.

More: Terminus-2 – DeepSeek V4 Pro (high) · Codex – GPT-6 Luna (high) · all comparisons