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

Comparison between Codex – GPT-5.6 Sol (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 – GPT-5.6 Sol (high) vs. Codex – GPT-5.6 Luna (low)
Metric	Codex – GPT-5.6 Sol (high)	Codex – GPT-5.6 Luna (low)
Geospatial Agent Index	75*	60* (partial: attempt 1 on 397 of 488 tasks)
Earth-Bench V2 score	68	44
GeoBenchX score	70	61
GS-QA2 score	87	76
GeoAgentBench score (guided GIS workflow; outside the index)	100	86
GeoAnalystBench score (guided GIS workflow; outside the index)	89	95
Raster and remote sensing score	78	70
Vector and overlay score	87	72
Climate and time series score	76	42
Spatial statistics and interpolation score	62	0
Mapping and cartography score	82	83
Recognising infeasible requests score	58	50
Cost per task	$0.21	$0.0057
Time per task	2.5 min	1.6 min
Tokens per attempt	180k	84k
Turns per attempt	9.5	7.1
Attempts decided	488	397
Input price per 1M tokens	$4.00	$0.20
Output price per 1M tokens	$20.00	$1.20
Context window	No data	No data
Image input	No data	No data
Developer	OpenAI	OpenAI

Charts

Partial coverage. 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

Attempts still to run

Data table: Geospatial Agent Index

Geospatial Agent Index
Model	Creator	Geospatial Agent Index	Range while attempts are pending	Benchmarks covered	Coverage (attempts)
Codex – GPT-5.6 Sol (high)	OpenAI	75*	No pending judgements; coverage incomplete; 195 results awaiting review	3 of 3	488 of 722 scheduled attempts

Cost per task

Average cost per task (USD) · Lower is better

Attempts still to run

How to read this chart

Not shown: partial coverage. 1 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)
Codex – GPT-5.6 Sol (high)	OpenAI	$0.21	488 of 722 scheduled attempts

Output tokens per task

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

Attempts still to run

How to read this chart

Not shown: partial coverage. 1 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)
Codex – GPT-5.6 Sol (high)	OpenAI	4k	488 of 722 scheduled attempts

Frequently asked questions

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

Not comparable yet: Codex – GPT-5.6 Luna (low) has partial coverage (59 of 150 GeoBenchX tasks), so it is not ranked. Codex – GPT-5.6 Sol (high): 488 of 722 scheduled attempts. 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 – GPT-5.6 Sol (high) or Codex – GPT-5.6 Luna (low)?

Codex – GPT-5.6 Luna (low), at $0.0057 against $0.21 for Codex – GPT-5.6 Sol (high).

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

Codex – GPT-5.6 Luna (low), at 1k against 4k for Codex – GPT-5.6 Sol (high).

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

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

More: Codex – GPT-5.6 Sol (high) · Codex – GPT-5.6 Luna (low) · all comparisons