Terminus-2 – GLM-4.7-Flash (thinking on) vs. Codex – GPT-6 Luna (low): geospatial agent comparison

Comparison between Terminus-2 – GLM-4.7-Flash (thinking on) and Codex – GPT-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

Terminus-2 – GLM-4.7-Flash (thinking on) vs. Codex – GPT-6 Luna (low)
Metric	Terminus-2 – GLM-4.7-Flash (thinking on)	Codex – GPT-6 Luna (low)
Geospatial Agent Index	43* (partial: attempt 1 on 478 of 488 tasks)	51* (partial: attempt 1 on 449 of 488 tasks)
Earth-Bench V2 score	44	44
GeoBenchX score	42	50
GS-QA2 score	44	59
GeoAgentBench score (guided GIS workflow; outside the index)	42	92
GeoAnalystBench score (guided GIS workflow; outside the index)	37	79
Raster and remote sensing score	43	55
Vector and overlay score	49	57
Climate and time series score	41	49
Spatial statistics and interpolation score	15	38
Mapping and cartography score	47	71
Recognising infeasible requests score	43	30
Cost per task	$0.036	$0.0031
Time per task	10.0 min	1.4 min
Tokens per attempt	520k	114k
Turns per attempt	26.0	7.8
Attempts decided	478	449
Input price per 1M tokens	$0.060	$0.10
Output price per 1M tokens	$0.40	$0.50
Context window	131,072	No data
Image input	No	No data
Developer	Z.ai	OpenAI

Charts

Partial coverage. Terminus-2 – GLM-4.7-Flash (thinking on): 211 of 221 GS-QA2 tasks; Codex – GPT-6 Luna (low): 111 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

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 – GLM-4.7-Flash (thinking on) or Codex – GPT-6 Luna (low)?

Not comparable yet: Terminus-2 – GLM-4.7-Flash (thinking on) has partial coverage (211 of 221 GS-QA2 tasks) and Codex – GPT-6 Luna (low) has partial coverage (111 of 150 GeoBenchX tasks), so it is not ranked. Terminus-2 – GLM-4.7-Flash (thinking on): 478 of 722 scheduled attempts (1 excluded). Codex – GPT-6 Luna (low): 449 of 722 scheduled attempts. Coverage is partial; scores can change as more attempts are decided.

Which is cheaper per task, Terminus-2 – GLM-4.7-Flash (thinking on) or Codex – GPT-6 Luna (low)?

Codex – GPT-6 Luna (low), at $0.0031 against $0.036 for Terminus-2 – GLM-4.7-Flash (thinking on).

Which writes fewer output tokens per task, Terminus-2 – GLM-4.7-Flash (thinking on) or Codex – GPT-6 Luna (low)?

Codex – GPT-6 Luna (low), at 1k against 14k for Terminus-2 – GLM-4.7-Flash (thinking on).

Which has the larger context window, Terminus-2 – GLM-4.7-Flash (thinking on) or Codex – GPT-6 Luna (low)?

Not known yet: Codex – GPT-6 Luna (low) has no context window data.

More: Terminus-2 – GLM-4.7-Flash (thinking on) · Codex – GPT-6 Luna (low) · all comparisons