Claude Code – Claude Opus 4.8 (high) vs. Codex – GPT-6 Luna (xhigh): geospatial agent comparison

Comparison between Claude Code – Claude Opus 4.8 (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

Claude Code – Claude Opus 4.8 (high) vs. Codex – GPT-6 Luna (xhigh)
Metric	Claude Code – Claude Opus 4.8 (high)	Codex – GPT-6 Luna (xhigh)
Geospatial Agent Index	51* (partial: attempt 1 on 105 of 320 tasks)	60*
Earth-Bench V2 score	47	56
GeoBenchX score	55	64
GeoAgentBench score (guided GIS workflow; outside the index)	93	96
GeoAnalystBench score (guided GIS workflow; outside the index)	100	100
Raster and remote sensing score	50	55
Vector and overlay score	100	50
Networks and routing score	No data	No data
Climate and time series score	50	63
Spatial statistics and interpolation score	17	43
Mapping and cartography score	83	69
Recognising infeasible requests score	38	62
Cost per task	$0.447	$0.010
Time per task	2.2 min	3.9 min
Tokens per attempt	197k	247k
Turns per attempt	8.0	10.2
Attempts decided	105	320
Input price per 1M tokens	$5.00	$0.10
Output price per 1M tokens	$25.00	$0.50
Context window	No data	No data
Image input	No data	No data
Developer	Anthropic	OpenAI

Charts

Partial coverage. Claude Code – Claude Opus 4.8 (high): 49 of 147 Earth-Bench V2 tasks; 56 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 Luna (xhigh)	OpenAI	60*	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. Claude Code – Claude Opus 4.8 (high).

Data table: Cost per task

Cost per task
Model	Creator	Cost per task	Coverage (attempts)
Codex – GPT-6 Luna (xhigh)	OpenAI	$0.010	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. Claude Code – Claude Opus 4.8 (high).

Data table: Time per task

Time per task
Model	Creator	Time per task	Coverage (attempts)
Codex – GPT-6 Luna (xhigh)	OpenAI	3.9 min	320 of 614 planned attempts

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Claude Code – Claude Opus 4.8 (high) or Codex – GPT-6 Luna (xhigh)?

Not comparable yet: Claude Code – Claude Opus 4.8 (high) has partial coverage (49 of 147 Earth-Bench V2 tasks; 56 of 173 GeoBenchX tasks), so it is not ranked. Claude Code – Claude Opus 4.8 (high): 105 of 614 planned attempts. Codex – GPT-6 Luna (xhigh): 320 of 614 planned attempts. Coverage is partial; scores can change as more attempts are decided.

Which is cheaper per task, Claude Code – Claude Opus 4.8 (high) or Codex – GPT-6 Luna (xhigh)?

Codex – GPT-6 Luna (xhigh), at $0.010 against $0.447 for Claude Code – Claude Opus 4.8 (high).

Which is faster per task, Claude Code – Claude Opus 4.8 (high) or Codex – GPT-6 Luna (xhigh)?

Claude Code – Claude Opus 4.8 (high), at 2.2 min against 3.9 min for Codex – GPT-6 Luna (xhigh).

Which has the larger context window, Claude Code – Claude Opus 4.8 (high) or Codex – GPT-6 Luna (xhigh)?

Not known yet: Claude Code – Claude Opus 4.8 (high) has no context window data and Codex – GPT-6 Luna (xhigh) has no context window data.

More: Claude Code – Claude Opus 4.8 (high) · Codex – GPT-6 Luna (xhigh) · all comparisons