GPT-5.6 Sol (medium), Codex vs. GPT-5.6 Luna (high), Codex
GPT-5.6 Sol (medium), Codex against GPT-5.6 Luna (high), Codex: Geospatial Agent Index, each evaluation, cost, time and tokens, on the same tasks and limits. Methodology.
Side by side
| Metric | GPT-5.6 Sol (medium), Codex | GPT-5.6 Luna (high), Codex |
|---|---|---|
| Geospatial Agent Index: Text only | 100, not every task attempted yet (19 of 488 tasks attempted) | 72 |
| Geospatial Agent Index: Text + vision | Still to run: Earth-Bench V2, GeoBenchX, GS-QA2, Vision agents | 71 |
| Earth-Bench V2 score | No data | 67 |
| GeoBenchX score | No data | 67 |
| GS-QA2 score | 100 | 81 |
| Vision agents score | No data | 69 |
| GeoAgentBench score (Guided workflows; not in the Agent Index) | No data | 98 |
| GeoAnalystBench score (Guided workflows; not in the Agent Index) | No data | 100 |
| Raster and remote sensing score | 100 | 78 |
| Vector and overlay score | No data | 79 |
| Climate and time series score | No data | 69 |
| Spatial statistics and interpolation score | No data | 38 |
| Mapping and cartography score | No data | 84 |
| Recognising infeasible requests score | No data | 53 |
| Cost per task | $0.060 | $0.016 |
| Time per task (at 100 output tokens/s) | 0.2 min | 1.4 min |
| Tokens per attempt | 66k | 252k |
| Turns per attempt | 6.1 | 12.3 |
| Attempts scored | 19 | 488 |
| Input price per 1M tokens | $4.00 | $0.20 |
| Output price per 1M tokens | $20.00 | $1.20 |
| Developer | OpenAI | OpenAI |
* Not every task attempted yet: the score may still change. What the asterisk means.
Charts
Not yet ranked. GPT-5.6 Sol (medium), Codex: Earth-Bench V2 not started; GeoBenchX not started; 19 of 221 GS-QA2 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
Top eight. Every model is in the table.
Data table: Geospatial Agent Index
| Model | Developer | Geospatial Agent Index | Status | Evaluations scored | Tasks attempted |
|---|---|---|---|---|---|
| GPT-5.6 Luna (high), Codex | OpenAI | 72 | Complete | 3 of 3 | 488 of 488 tasks |
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. 1 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 |
|---|---|---|---|
| GPT-5.6 Luna (high), Codex | OpenAI | $0.016 | 488 of 488 tasks |
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. 1 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 |
|---|---|---|---|
| GPT-5.6 Luna (high), Codex | OpenAI | 5k | 488 of 488 tasks |
Frequently asked questions
Which scores higher on the Geospatial Agent Index, GPT-5.6 Sol (medium), Codex or GPT-5.6 Luna (high), Codex?
Which is cheaper per task, GPT-5.6 Sol (medium), Codex or GPT-5.6 Luna (high), Codex?
Which writes fewer output tokens per task, GPT-5.6 Sol (medium), Codex or GPT-5.6 Luna (high), Codex?
More: GPT-5.6 Sol (medium), Codex · GPT-5.6 Luna (high), Codex · All comparisons