DeepSeek V4.1 Flash (max), Codex vs. gpt-oss-20b (high), Codex
DeepSeek V4.1 Flash (max), Codex against gpt-oss-20b (high), Codex: Geospatial Agent Index, each evaluation, cost, time and tokens, on the same tasks and limits. Methodology.
Side by side
| Metric | DeepSeek V4.1 Flash (max), Codex | gpt-oss-20b (high), Codex |
|---|---|---|
| Geospatial Agent Index: Text only | 71 | 9 |
| Geospatial Agent Index: Text + vision | 73 | No image input |
| Earth-Bench V2 score | 66 | 6 |
| GeoBenchX score | 56 | 10 |
| GS-QA2 score | 89 | 12 |
| Vision agents score | 80 | No image input |
| GeoAgentBench score (Guided workflows; not in the Agent Index) | 90 | 10 |
| GeoAnalystBench score (Guided workflows; not in the Agent Index) | 88 | 11 |
| OGD4All score (standalone; in no index) | No data | No data |
| GeoNatureAgent score (standalone; in no index) | No data | No data |
| MultiGlobeQA score (standalone; in no index) | No data | No data |
| GeoAgentEval score (standalone; in no index) | No data | No data |
| Remote sensing and raster analysis score | 83 | 11 |
| GIS analysis score | 90 | 12 |
| Climate and time series score | 58 | 5 |
| Spatial statistics score | 46 | 0 |
| Making maps score | 72 | 4 |
| Recognising infeasible requests score | 41 | 17 |
| Cost per task | $0.067 | $0.094 |
| Time per task (at 100 output tokens/s) | 8.6 min | 4.8 min |
| Tokens per attempt | 1.17M | 457k |
| Turns per attempt | 23.4 | 24.2 |
| Input price per 1M tokens | $0.30 | $0.20 |
| Output price per 1M tokens | $1.20 | $0.30 |
| Context window | 1,048,576 | 128,000 |
| Image input | Yes | No |
| Developer | Other | OpenAI |
Charts
Geospatial Agent Index
Equal average of Earth-Bench V2, GeoBenchX and GS-QA2, 0 to 100 · Higher is better
Data table: Geospatial Agent Index
| Model | Developer | Geospatial Agent Index |
|---|---|---|
| DeepSeek V4.1 Flash (max), Codex | Other | 71 |
| gpt-oss-20b (high), Codex | OpenAI | 9 |
Cost per task
Average cost per task (USD) · Lower is better
Data table: Cost per task
| Model | Developer | Cost per task |
|---|---|---|
| DeepSeek V4.1 Flash (max), Codex | Other | $0.067 |
| gpt-oss-20b (high), Codex | OpenAI | $0.094 |
Output tokens per task
Average output tokens per attempt, reasoning included · Lower is better
Data table: Output tokens per task
| Model | Developer | Output tokens per task |
|---|---|---|
| gpt-oss-20b (high), Codex | OpenAI | 23k |
| DeepSeek V4.1 Flash (max), Codex | Other | 38k |
Frequently asked questions
Which scores higher on the Geospatial Agent Index, DeepSeek V4.1 Flash (max), Codex or gpt-oss-20b (high), Codex?
DeepSeek V4.1 Flash (max), Codex, 71 to 9.
Which is cheaper per task, DeepSeek V4.1 Flash (max), Codex or gpt-oss-20b (high), Codex?
DeepSeek V4.1 Flash (max), Codex, $0.067 to $0.094.
Which writes fewer output tokens per task, DeepSeek V4.1 Flash (max), Codex or gpt-oss-20b (high), Codex?
gpt-oss-20b (high), Codex, 23k to 38k.
Which has the larger context window, DeepSeek V4.1 Flash (max), Codex or gpt-oss-20b (high), Codex?
DeepSeek V4.1 Flash (max), Codex, 1,048,576 tokens to 128,000 tokens.
More: DeepSeek V4.1 Flash (max), Codex · gpt-oss-20b (high), Codex · All comparisons