Terminus-2 – GLM-5.2 (high) vs. Codex – gpt-oss-120b (high): geospatial agent comparison

Comparison between Terminus-2 – GLM-5.2 (high) and Codex – gpt-oss-120b (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 – GLM-5.2 (high) vs. Codex – gpt-oss-120b (high)
Metric	Terminus-2 – GLM-5.2 (high)	Codex – gpt-oss-120b (high)
Geospatial Agent Index	62*	47* (partial: attempt 1 on 49 of 565 tasks)
Earth-Bench V2 score	56	62
GeoBenchX score	58	31
GS-QA2 score	72	No data
GeoAgentBench score (guided GIS workflow; outside the index)	94	No data
GeoAnalystBench score (guided GIS workflow; outside the index)	100	No data
Raster and remote sensing score	67	64
Vector and overlay score	69	No data
Networks and routing score	No data	No data
Climate and time series score	62	0
Spatial statistics and interpolation score	43	0
Mapping and cartography score	78	44
Recognising infeasible requests score	41	25
Cost per task	$0.250	$0.236
Time per task	5.8 min	12.4 min
Tokens per attempt	374k	642k
Turns per attempt	13.5	29.7
Attempts decided	564	44
Input price per 1M tokens	$1.40	$0.35
Output price per 1M tokens	$4.40	$0.75
Context window	262,144	128,000
Image input	No	No
Developer	Z.ai	OpenAI

Charts

Partial coverage. Terminus-2 – GLM-5.2 (high): 244 of 245 GS-QA2 tasks; 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

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. Terminus-2 – GLM-5.2 (high), Codex – gpt-oss-120b (high).

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. Terminus-2 – GLM-5.2 (high), Codex – gpt-oss-120b (high).

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 – GLM-5.2 (high) or Codex – gpt-oss-120b (high)?

Not comparable yet: Terminus-2 – GLM-5.2 (high) has partial coverage (244 of 245 GS-QA2 tasks) and 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. Terminus-2 – GLM-5.2 (high): 564 of 859 planned attempts. Codex – gpt-oss-120b (high): 44 of 614 planned attempts. Coverage is partial; scores can change as more attempts are decided.

Which is cheaper per task, Terminus-2 – GLM-5.2 (high) or Codex – gpt-oss-120b (high)?

Codex – gpt-oss-120b (high), at $0.236 against $0.250 for Terminus-2 – GLM-5.2 (high).

Which writes fewer output tokens per task, Terminus-2 – GLM-5.2 (high) or Codex – gpt-oss-120b (high)?

Terminus-2 – GLM-5.2 (high), at 25k against 29k for Codex – gpt-oss-120b (high).

Which has the larger context window, Terminus-2 – GLM-5.2 (high) or Codex – gpt-oss-120b (high)?

Terminus-2 – GLM-5.2 (high), at 262,144 tokens against 128,000 tokens for Codex – gpt-oss-120b (high).

More: Terminus-2 – GLM-5.2 (high) · Codex – gpt-oss-120b (high) · all comparisons