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

Comparison between Terminus-2 – gpt-oss-120b (low) and Codex – GPT-5.6 Sol (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 – gpt-oss-120b (low) vs. Codex – GPT-5.6 Sol (high)
Metric	Terminus-2 – gpt-oss-120b (low)	Codex – GPT-5.6 Sol (high)
Geospatial Agent Index	31*	79* (partial: attempt 1 on 360 of 488 tasks)
Earth-Bench V2 score	28	76
GeoBenchX score	37	72
GS-QA2 score	29	89
GeoAgentBench score (guided GIS workflow; outside the index)	60	100
GeoAnalystBench score (guided GIS workflow; outside the index)	47	100
Raster and remote sensing score	25	83
Vector and overlay score	34	87
Climate and time series score	29	87
Spatial statistics and interpolation score	8	50
Mapping and cartography score	21	92
Recognising infeasible requests score	60	65
Cost per task	$0.0046	$0.17
Time per task	0.7 min	2.0 min
Tokens per attempt	11k	141k
Turns per attempt	2.9	8.4
Attempts decided	488	350
Input price per 1M tokens	$0.35	$4.00
Output price per 1M tokens	$0.75	$20.00
Context window	128,000	No data
Image input	No	No data
Developer	OpenAI	OpenAI

Charts

Partial coverage. Codex – GPT-5.6 Sol (high): 93 of 117 Earth-Bench V2 tasks; 63 of 150 GeoBenchX tasks; 204 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

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)
Terminus-2 – gpt-oss-120b (low)	OpenAI	31*	No pending judgements; coverage incomplete	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)
Terminus-2 – gpt-oss-120b (low)	OpenAI	$0.0046	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)
Terminus-2 – gpt-oss-120b (low)	OpenAI	2k	488 of 722 scheduled attempts

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Terminus-2 – gpt-oss-120b (low) or Codex – GPT-5.6 Sol (high)?

Not comparable yet: Codex – GPT-5.6 Sol (high) has partial coverage (93 of 117 Earth-Bench V2 tasks; 63 of 150 GeoBenchX tasks; 204 of 221 GS-QA2 tasks), so it is not ranked. Terminus-2 – gpt-oss-120b (low): 488 of 722 scheduled attempts. Codex – GPT-5.6 Sol (high): 350 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 (low) or Codex – GPT-5.6 Sol (high)?

Terminus-2 – gpt-oss-120b (low), at $0.0046 against $0.17 for Codex – GPT-5.6 Sol (high).

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

Terminus-2 – gpt-oss-120b (low), at 2k against 3k for Codex – GPT-5.6 Sol (high).

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

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

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