Terminus-2 – gpt-oss-120b (high) vs. Codex – GPT-5.6 Luna (xhigh): geospatial agent comparison

Comparison between Terminus-2 – gpt-oss-120b (high) and Codex – GPT-5.6 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

Terminus-2 – gpt-oss-120b (high) vs. Codex – GPT-5.6 Luna (xhigh)
Metric	Terminus-2 – gpt-oss-120b (high)	Codex – GPT-5.6 Luna (xhigh)
Geospatial Agent Index	46* (partial: attempt 1 on 481 of 488 tasks)	77* (partial: attempt 1 on 210 of 488 tasks)
Earth-Bench V2 score	50	86
GeoBenchX score	45	60
GS-QA2 score	41	85
GeoAgentBench score (guided GIS workflow; outside the index)	70	98
GeoAnalystBench score (guided GIS workflow; outside the index)	53	100
Raster and remote sensing score	44	82
Vector and overlay score	41	86
Climate and time series score	53	90
Spatial statistics and interpolation score	15	33
Mapping and cartography score	40	75
Recognising infeasible requests score	58	50
Cost per task	$0.026	$0.012
Time per task	4.8 min	2.5 min
Tokens per attempt	58k	176k
Turns per attempt	5.8	9.7
Attempts decided	481	210
Input price per 1M tokens	$0.35	$0.20
Output price per 1M tokens	$0.75	$1.20
Context window	128,000	No data
Image input	No	No data
Developer	OpenAI	OpenAI

Charts

Partial coverage. Terminus-2 – gpt-oss-120b (high): 214 of 221 GS-QA2 tasks; Codex – GPT-5.6 Luna (xhigh): 49 of 117 Earth-Bench V2 tasks; 20 of 150 GeoBenchX tasks; 141 of 221 GS-QA2 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 – gpt-oss-120b (high) or Codex – GPT-5.6 Luna (xhigh)?

Not comparable yet: Terminus-2 – gpt-oss-120b (high) has partial coverage (214 of 221 GS-QA2 tasks) and Codex – GPT-5.6 Luna (xhigh) has partial coverage (49 of 117 Earth-Bench V2 tasks; 20 of 150 GeoBenchX tasks; 141 of 221 GS-QA2 tasks), so it is not ranked. Terminus-2 – gpt-oss-120b (high): 481 of 722 scheduled attempts. Codex – GPT-5.6 Luna (xhigh): 210 of 722 scheduled attempts. Coverage is partial; scores can change as more attempts are decided.

Which is cheaper per task, Terminus-2 – gpt-oss-120b (high) or Codex – GPT-5.6 Luna (xhigh)?

Codex – GPT-5.6 Luna (xhigh), at $0.012 against $0.026 for Terminus-2 – gpt-oss-120b (high).

Which writes fewer output tokens per task, Terminus-2 – gpt-oss-120b (high) or Codex – GPT-5.6 Luna (xhigh)?

Codex – GPT-5.6 Luna (xhigh), at 4k against 15k for Terminus-2 – gpt-oss-120b (high).

Which has the larger context window, Terminus-2 – gpt-oss-120b (high) or Codex – GPT-5.6 Luna (xhigh)?

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

More: Terminus-2 – gpt-oss-120b (high) · Codex – GPT-5.6 Luna (xhigh) · all comparisons