Claude Code – GLM-5.3-Flash (max) vs. Codex – GPT-6 Sol (medium): geospatial agent comparison

Comparison between Claude Code – GLM-5.3-Flash (max) and Codex – GPT-6 Sol (medium) on the Geospatial Agent Index, each benchmark, cost, time and token use, from the same tasks, agent and limits. Methodology.

Side by side

Claude Code – GLM-5.3-Flash (max) vs. Codex – GPT-6 Sol (medium)
Metric	Claude Code – GLM-5.3-Flash (max)	Codex – GPT-6 Sol (medium)
Geospatial Agent Index	72* (partial: attempt 1 on 449 of 488 tasks)	77* (partial: attempt 1 on 193 of 488 tasks)
Earth-Bench V2 score	69	80
GeoBenchX score	70	64
GS-QA2 score	76	88
GeoAgentBench score (guided GIS workflow; outside the index)	No data	100
GeoAnalystBench score (guided GIS workflow; outside the index)	No data	No data
Raster and remote sensing score	74	87
Vector and overlay score	79	86
Climate and time series score	67	83
Spatial statistics and interpolation score	78	50
Mapping and cartography score	74	100
Recognising infeasible requests score	65	50
Cost per task	$0.093	$0.048
Time per task	14.8 min	1.3 min
Tokens per attempt	962k	87k
Turns per attempt	18.9	6.5
Attempts decided	449	193
Input price per 1M tokens	$0.15	$2.00
Output price per 1M tokens	$0.50	$10.00
Context window	1,048,576	No data
Image input	Yes	No data
Developer	Z.ai	OpenAI

Charts

Partial coverage. Claude Code – GLM-5.3-Flash (max): 108 of 117 Earth-Bench V2 tasks; 120 of 150 GeoBenchX tasks; Codex – GPT-6 Sol (medium): 55 of 117 Earth-Bench V2 tasks; 11 of 150 GeoBenchX tasks; 127 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, Claude Code – GLM-5.3-Flash (max) or Codex – GPT-6 Sol (medium)?

Not comparable yet: Claude Code – GLM-5.3-Flash (max) has partial coverage (108 of 117 Earth-Bench V2 tasks; 120 of 150 GeoBenchX tasks) and Codex – GPT-6 Sol (medium) has partial coverage (55 of 117 Earth-Bench V2 tasks; 11 of 150 GeoBenchX tasks; 127 of 221 GS-QA2 tasks), so it is not ranked. Claude Code – GLM-5.3-Flash (max): 449 of 722 scheduled attempts (8 excluded). Codex – GPT-6 Sol (medium): 193 of 722 scheduled attempts. Coverage is partial; scores can change as more attempts are decided.

Which is cheaper per task, Claude Code – GLM-5.3-Flash (max) or Codex – GPT-6 Sol (medium)?

Codex – GPT-6 Sol (medium), at $0.048 against $0.093 for Claude Code – GLM-5.3-Flash (max).

Which writes fewer output tokens per task, Claude Code – GLM-5.3-Flash (max) or Codex – GPT-6 Sol (medium)?

Codex – GPT-6 Sol (medium), at 1k against 29k for Claude Code – GLM-5.3-Flash (max).

Which has the larger context window, Claude Code – GLM-5.3-Flash (max) or Codex – GPT-6 Sol (medium)?

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

More: Claude Code – GLM-5.3-Flash (max) · Codex – GPT-6 Sol (medium) · all comparisons