Mistral Large 3 (Non-reasoning), Terminus-2 vs. GLM-5.2 (max), Claude Code

Mistral Large 3 (Non-reasoning), Terminus-2 against GLM-5.2 (max), Claude Code: Geospatial Agent Index, each evaluation, cost, time and tokens, on the same tasks and limits. The harnesses differ, so part of any gap can come from the harness. Methodology.

Side by side

Mistral Large 3 (Non-reasoning), Terminus-2 vs. GLM-5.2 (max), Claude Code
Metric	Mistral Large 3 (Non-reasoning), Terminus-2	GLM-5.2 (max), Claude Code
Geospatial Agent Index: Text only	33, not every task attempted yet	73, not every task attempted yet
Geospatial Agent Index: Text + vision	Still to run: GS-QA2, Vision agents	No image input
Earth-Bench V2 score	31	71
GeoBenchX score	29	66
GS-QA2 score	39	83
Vision agents score	No data	No image input
GeoAgentBench score (Guided workflows; not in the Agent Index)	46	No data
GeoAnalystBench score (Guided workflows; not in the Agent Index)	47	No data
Raster and remote sensing score	29	80
Vector and overlay score	41	81
Climate and time series score	34	72
Spatial statistics and interpolation score	8	46
Mapping and cartography score	33	84
Recognising infeasible requests score	33	52
Cost per task	$0.026	$0.34
Time per task (at 100 output tokens/s)	1.1 min	6.3 min
Tokens per attempt	43k	617k
Turns per attempt	5.2	15.4
Attempts scored	487	486
Input price per 1M tokens	$0.50	$1.40
Output price per 1M tokens	$1.50	$4.40
Context window	256,000	262,144
Image input	Yes	No
Developer	Mistral AI	Z.ai

* Not every task attempted yet: the score may still change. What the asterisk means.

Charts

Not yet ranked. Mistral Large 3 (Non-reasoning), Terminus-2: 220 of 221 GS-QA2 tasks attempted; GLM-5.2 (max), Claude Code: 115 of 117 Earth-Bench V2 tasks attempted. Grey placeholders mark these entries in the index, cost and output token charts; their height is not a value. Bars appear once every task has an attempt. Results so far are in the side-by-side table.

Geospatial Agent Index

Equal average of Earth-Bench V2, GeoBenchX and GS-QA2, 0 to 100 · Higher is better

Data table: Geospatial Agent Index

Geospatial Agent Index
Model	Developer	Geospatial Agent Index	Status	Evaluations scored	Tasks attempted

Cost per task

Average cost per task (USD) · Lower is better

How to read this chart

Not shown: not yet ranked. 2 entries without an attempt on every index task. What is still to run is on the models page.

Data table: Cost per task

Cost per task
Model	Developer	Cost per task	Tasks attempted

Output tokens per task

Average output tokens per attempt, reasoning included · Lower is better

How to read this chart

Not shown: not yet ranked. 2 entries without an attempt on every index task. What is still to run is on the models page.

Data table: Output tokens per task

Output tokens per task
Model	Developer	Output tokens per task	Tasks attempted

Frequently asked questions

Which scores higher on the Geospatial Agent Index, Mistral Large 3 (Non-reasoning), Terminus-2 or GLM-5.2 (max), Claude Code?

Not comparable yet: Mistral Large 3 (Non-reasoning), Terminus-2 is not yet ranked (220 of 221 GS-QA2 tasks attempted) and GLM-5.2 (max), Claude Code is not yet ranked (115 of 117 Earth-Bench V2 tasks attempted). Mistral Large 3 (Non-reasoning), Terminus-2: 487 of 488 tasks attempted. GLM-5.2 (max), Claude Code: 486 of 488 tasks attempted. Scores can change as more tasks are attempted.

Which is cheaper per task, Mistral Large 3 (Non-reasoning), Terminus-2 or GLM-5.2 (max), Claude Code?

Mistral Large 3 (Non-reasoning), Terminus-2, $0.026 to $0.34.

Which writes fewer output tokens per task, Mistral Large 3 (Non-reasoning), Terminus-2 or GLM-5.2 (max), Claude Code?

Mistral Large 3 (Non-reasoning), Terminus-2, 4k to 28k.

Which has the larger context window, Mistral Large 3 (Non-reasoning), Terminus-2 or GLM-5.2 (max), Claude Code?

GLM-5.2 (max), Claude Code, 262,144 tokens to 256,000 tokens.

More: Mistral Large 3 (Non-reasoning), Terminus-2 · GLM-5.2 (max), Claude Code · All comparisons