Mistral Large 3 (Non-reasoning), Terminus-2 vs. Qwen 3.8 27B (xhigh), Terminus-2
Mistral Large 3 (Non-reasoning), Terminus-2 against Qwen 3.8 27B (xhigh), Terminus-2: Geospatial Agent Index, each evaluation, cost, time and tokens, on the same tasks and limits. Methodology.
Side by side
| Metric | Mistral Large 3 (Non-reasoning), Terminus-2 | Qwen 3.8 27B (xhigh), Terminus-2 |
|---|---|---|
| Geospatial Agent Index: Text only | 33, not every task attempted yet | 37, not every task attempted yet (27 of 488 tasks attempted) |
| Geospatial Agent Index: Text + vision | Still to run: GS-QA2, Vision agents | Still to run: Earth-Bench V2, GeoBenchX, GS-QA2, Vision agents |
| Earth-Bench V2 score | 31 | 37 |
| GeoBenchX score | 29 | No data |
| GS-QA2 score | 39 | No data |
| Vision agents score | No data | No data |
| GeoAgentBench score (Guided workflows; not in the Agent Index) | 46 | 60 |
| GeoAnalystBench score (Guided workflows; not in the Agent Index) | 47 | 100 |
| Raster and remote sensing score | 29 | 38 |
| Vector and overlay score | 41 | No data |
| Climate and time series score | 34 | 36 |
| Spatial statistics and interpolation score | 8 | No data |
| Mapping and cartography score | 33 | No data |
| Recognising infeasible requests score | 33 | No data |
| Cost per task | $0.026 | $0.055 |
| Time per task (at 100 output tokens/s) | 1.1 min | 9.2 min |
| Tokens per attempt | 43k | 66k |
| Turns per attempt | 5.2 | 7.0 |
| Attempts scored | 487 | 27 |
| Input price per 1M tokens | $0.50 | $0.45 |
| Output price per 1M tokens | $1.50 | $3.20 |
| Context window | 256,000 | 262,144 |
| Image input | Yes | Yes |
| Developer | Mistral AI | Alibaba (Qwen) |
* 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; Qwen 3.8 27B (xhigh), Terminus-2: 27 of 117 Earth-Bench V2 tasks; GeoBenchX not started; GS-QA2 not started 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
Top eight. Every model is in the table.
Data table: Geospatial Agent Index
| Model | Developer | Geospatial Agent Index | Status | Evaluations scored | Tasks attempted |
|---|
Cost per task
Average cost per task (USD) · Lower is better
Top eight. Every model is in the table.
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
| Model | Developer | Cost per task | Tasks attempted |
|---|
Output tokens per task
Average output tokens per attempt, reasoning included · Lower is better
Top eight. Every model is in the table.
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
| 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 Qwen 3.8 27B (xhigh), Terminus-2?
Which is cheaper per task, Mistral Large 3 (Non-reasoning), Terminus-2 or Qwen 3.8 27B (xhigh), Terminus-2?
Which writes fewer output tokens per task, Mistral Large 3 (Non-reasoning), Terminus-2 or Qwen 3.8 27B (xhigh), Terminus-2?
Which has the larger context window, Mistral Large 3 (Non-reasoning), Terminus-2 or Qwen 3.8 27B (xhigh), Terminus-2?
More: Mistral Large 3 (Non-reasoning), Terminus-2 · Qwen 3.8 27B (xhigh), Terminus-2 · All comparisons