Codex – DeepSeek V4 Pro (high) vs. Codex – GPT-5.6 Luna (xhigh): geospatial agent comparison
Comparison between Codex – DeepSeek V4 Pro (high) and Codex – GPT-5.6 Luna (xhigh) on the Geospatial Agent Index, each benchmark, cost, time and token use, from the same tasks, agent and limits. Methodology.
Side by side
| Metric | Codex – DeepSeek V4 Pro (high) | Codex – GPT-5.6 Luna (xhigh) |
|---|---|---|
| Geospatial Agent Index | 62* (partial: attempt 1 on 116 of 488 tasks) | 77* (partial: attempt 1 on 210 of 488 tasks) |
| Earth-Bench V2 score | 57 | 86 |
| GeoBenchX score | 66 | 60 |
| GS-QA2 score | No data | 85 |
| GeoAgentBench score (guided GIS workflow; outside the index) | No data | 98 |
| GeoAnalystBench score (guided GIS workflow; outside the index) | No data | 100 |
| Raster and remote sensing score | 62 | 82 |
| Vector and overlay score | 0 | 86 |
| Climate and time series score | 42 | 90 |
| Spatial statistics and interpolation score | 17 | 33 |
| Mapping and cartography score | 85 | 75 |
| Recognising infeasible requests score | 65 | 50 |
| Cost per task | $0.64 | $0.012 |
| Time per task | 10.3 min | 2.5 min |
| Tokens per attempt | 828k | 176k |
| Turns per attempt | 20.8 | 9.7 |
| Attempts decided | 116 | 210 |
| Input price per 1M tokens | $1.32 | $0.20 |
| Output price per 1M tokens | $3.96 | $1.20 |
| Context window | 1,048,576 | No data |
| Image input | No | No data |
| Developer | DeepSeek | OpenAI |
Charts
Partial coverage. Codex – DeepSeek V4 Pro (high): 28 of 117 Earth-Bench V2 tasks; 88 of 150 GeoBenchX tasks; GS-QA2 incomplete; Codex – GPT-5.6 Luna (xhigh): 49 of 117 Earth-Bench V2 tasks; 20 of 150 GeoBenchX tasks; 141 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, Codex – DeepSeek V4 Pro (high) or Codex – GPT-5.6 Luna (xhigh)?
Which is cheaper per task, Codex – DeepSeek V4 Pro (high) or Codex – GPT-5.6 Luna (xhigh)?
Which writes fewer output tokens per task, Codex – DeepSeek V4 Pro (high) or Codex – GPT-5.6 Luna (xhigh)?
Which has the larger context window, Codex – DeepSeek V4 Pro (high) or Codex – GPT-5.6 Luna (xhigh)?
More: Codex – DeepSeek V4 Pro (high) · Codex – GPT-5.6 Luna (xhigh) · all comparisons