Terminus-2 – Gemini 3.1 Flash-Lite (low) vs. Codex – GPT-5.6 Sol (high): geospatial agent comparison
Comparison between Terminus-2 – Gemini 3.1 Flash-Lite (low) and Codex – GPT-5.6 Sol (high) 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 – Gemini 3.1 Flash-Lite (low) | Codex – GPT-5.6 Sol (high) |
|---|---|---|
| Geospatial Agent Index | 48* (partial: attempt 1 on 177 of 488 tasks) | 79* (partial: attempt 1 on 360 of 488 tasks) |
| Earth-Bench V2 score | 44 | 76 |
| GeoBenchX score | 51 | 72 |
| GS-QA2 score | No data | 89 |
| GeoAgentBench score (guided GIS workflow; outside the index) | 52 | 100 |
| GeoAnalystBench score (guided GIS workflow; outside the index) | 63 | 100 |
| Raster and remote sensing score | 39 | 83 |
| Vector and overlay score | 40 | 87 |
| Climate and time series score | 45 | 87 |
| Spatial statistics and interpolation score | 8 | 50 |
| Mapping and cartography score | 54 | 92 |
| Recognising infeasible requests score | 62 | 65 |
| Cost per task | $0.012 | $0.17 |
| Time per task | 1.3 min | 2.0 min |
| Tokens per attempt | 39k | 141k |
| Turns per attempt | 5.2 | 8.4 |
| Attempts decided | 177 | 350 |
| Input price per 1M tokens | $0.25 | $4.00 |
| Output price per 1M tokens | $1.50 | $20.00 |
| Context window | 1,048,576 | No data |
| Image input | Yes | No data |
| Developer | OpenAI |
Charts
Partial coverage. Terminus-2 – Gemini 3.1 Flash-Lite (low): 27 of 117 Earth-Bench V2 tasks; GS-QA2 incomplete; Codex – GPT-5.6 Sol (high): 93 of 117 Earth-Bench V2 tasks; 63 of 150 GeoBenchX tasks; 204 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 – Gemini 3.1 Flash-Lite (low) or Codex – GPT-5.6 Sol (high)?
Which is cheaper per task, Terminus-2 – Gemini 3.1 Flash-Lite (low) or Codex – GPT-5.6 Sol (high)?
Which writes fewer output tokens per task, Terminus-2 – Gemini 3.1 Flash-Lite (low) or Codex – GPT-5.6 Sol (high)?
Which has the larger context window, Terminus-2 – Gemini 3.1 Flash-Lite (low) or Codex – GPT-5.6 Sol (high)?
More: Terminus-2 – Gemini 3.1 Flash-Lite (low) · Codex – GPT-5.6 Sol (high) · all comparisons