Terminus-2 – Gemma 4 26B A4B (thinking on) vs. Codex – GPT-6 Sol (medium): geospatial agent comparison
Comparison between Terminus-2 – Gemma 4 26B A4B (thinking on) 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
| Metric | Terminus-2 – Gemma 4 26B A4B (thinking on) | Codex – GPT-6 Sol (medium) |
|---|---|---|
| Geospatial Agent Index | 58* (partial: attempt 1 on 457 of 488 tasks) | 77* (partial: attempt 1 on 193 of 488 tasks) |
| Earth-Bench V2 score | 46 | 80 |
| GeoBenchX score | 63 | 64 |
| GS-QA2 score | 64 | 88 |
| GeoAgentBench score (guided GIS workflow; outside the index) | 86 | 100 |
| GeoAnalystBench score (guided GIS workflow; outside the index) | 63 | No data |
| Raster and remote sensing score | 64 | 87 |
| Vector and overlay score | 60 | 86 |
| Climate and time series score | 47 | 83 |
| Spatial statistics and interpolation score | 31 | 50 |
| Mapping and cartography score | 70 | 100 |
| Recognising infeasible requests score | 63 | 50 |
| Cost per task | $0.018 | $0.048 |
| Time per task | 11.5 min | 1.3 min |
| Tokens per attempt | 142k | 87k |
| Turns per attempt | 13.2 | 6.5 |
| Attempts decided | 457 | 193 |
| Input price per 1M tokens | $0.10 | $2.00 |
| Output price per 1M tokens | $0.30 | $10.00 |
| Context window | 256,000 | No data |
| Image input | Yes | No data |
| Developer | OpenAI |
Charts
Partial coverage. Terminus-2 – Gemma 4 26B A4B (thinking on): 190 of 221 GS-QA2 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
First eight selected entries in metric order. Full results in table view.
Data table: 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
First eight selected entries in metric order. Full results in table view.
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
| Model | Creator | Cost per task | Coverage (attempts) |
|---|
Output tokens per task
Average output tokens per attempt, reasoning included · Lower is better
First eight selected entries in metric order. Full results in table view.
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
| Model | Creator | Output tokens per task | Coverage (attempts) |
|---|
Frequently asked questions
Which scores higher on the Geospatial Agent Index, Terminus-2 – Gemma 4 26B A4B (thinking on) or Codex – GPT-6 Sol (medium)?
Which is cheaper per task, Terminus-2 – Gemma 4 26B A4B (thinking on) or Codex – GPT-6 Sol (medium)?
Which writes fewer output tokens per task, Terminus-2 – Gemma 4 26B A4B (thinking on) or Codex – GPT-6 Sol (medium)?
Which has the larger context window, Terminus-2 – Gemma 4 26B A4B (thinking on) or Codex – GPT-6 Sol (medium)?
More: Terminus-2 – Gemma 4 26B A4B (thinking on) · Codex – GPT-6 Sol (medium) · all comparisons