Codex – gpt-oss-120b (high) vs. Codex – GPT-6 Luna (xhigh): geospatial agent comparison

Comparison between Codex – gpt-oss-120b (high) and Codex – GPT-6 Luna (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-oss-120b (high) vs. Codex – GPT-6 Luna (xhigh)
Metric	Codex – gpt-oss-120b (high)	Codex – GPT-6 Luna (xhigh)
Geospatial Agent Index	47* (partial: attempt 1 on 49 of 565 tasks)	64*
Earth-Bench V2 score	62	56
GeoBenchX score	31	64
GS-QA2 score	No data	72
GeoAgentBench score (guided GIS workflow; outside the index)	No data	96
GeoAnalystBench score (guided GIS workflow; outside the index)	No data	100
Raster and remote sensing score	64	67
Vector and overlay score	No data	68
Networks and routing score	No data	No data
Climate and time series score	0	63
Spatial statistics and interpolation score	0	43
Mapping and cartography score	44	69
Recognising infeasible requests score	25	62
Cost per task	$0.236	$0.0076
Time per task	12.4 min	2.8 min
Tokens per attempt	642k	190k
Turns per attempt	29.7	9.0
Attempts decided	44	565
Input price per 1M tokens	$0.35	$0.10
Output price per 1M tokens	$0.75	$0.50
Context window	128,000	No data
Image input	No	No data
Developer	OpenAI	OpenAI

Charts

Partial coverage. Codex – gpt-oss-120b (high): 8 of 147 Earth-Bench V2 tasks; 41 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 Luna (xhigh)	OpenAI	64*	No pending judgements; coverage incomplete; 177 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 – gpt-oss-120b (high).

Data table: Cost per task

Cost per task
Model	Creator	Cost per task	Coverage (attempts)
Codex – GPT-6 Luna (xhigh)	OpenAI	$0.0076	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 – gpt-oss-120b (high).

Data table: Output tokens per task

Output tokens per task
Model	Creator	Output tokens per task	Coverage (attempts)
Codex – GPT-6 Luna (xhigh)	OpenAI	7k	565 of 859 planned attempts

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Codex – gpt-oss-120b (high) or Codex – GPT-6 Luna (xhigh)?

Not comparable yet: Codex – gpt-oss-120b (high) has partial coverage (8 of 147 Earth-Bench V2 tasks; 41 of 173 GeoBenchX tasks; GS-QA2 incomplete), so it is not ranked. Codex – gpt-oss-120b (high): 44 of 614 planned attempts. Codex – GPT-6 Luna (xhigh): 565 of 859 planned attempts. Coverage is partial; scores can change as more attempts are decided.

Which is cheaper per task, Codex – gpt-oss-120b (high) or Codex – GPT-6 Luna (xhigh)?

Codex – GPT-6 Luna (xhigh), at $0.0076 against $0.236 for Codex – gpt-oss-120b (high).

Which writes fewer output tokens per task, Codex – gpt-oss-120b (high) or Codex – GPT-6 Luna (xhigh)?

Codex – GPT-6 Luna (xhigh), at 7k against 29k for Codex – gpt-oss-120b (high).

Which has the larger context window, Codex – gpt-oss-120b (high) or Codex – GPT-6 Luna (xhigh)?

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

More: Codex – gpt-oss-120b (high) · Codex – GPT-6 Luna (xhigh) · all comparisons