DeepSeek V4.1 Flash (max), Claude Code vs DeepSeek V4.1 Flash (max), Codex
Results updated 31 October 2026 · In Claude Code and Codex, so part of any gap can come from the harness · How we benchmark
Verdict
DeepSeek V4.1 Flash (max), Codex beats DeepSeek V4.1 Flash (max), Claude Code by 3 points, and is cheaper and faster.
- Cost per task
- $0.20 vs $0.067
- Time per task
- 10.9 min vs 8.6 min
- Tokens per attempt
- 1.58M vs 1.17M
- Image input
- Yes vs Yes
DeepSeek V4.1 Flash (max), Codex scores higher on Earth-Bench V2 and GeoBenchX; they are level on GS-QA2. DeepSeek V4.1 Flash (max), Codex is cheaper and faster: $0.067 against $0.20 per task, and 8.6 min against 10.9 min.
Where they differ most
By kind of work, share of tasks passed, 0 to 100 · Higher is better
| Kind of work | DeepSeek V4.1 Flash (max), Claude Code | DeepSeek V4.1 Flash (max), Codex |
|---|---|---|
| Spatial statistics | 31 | 46 |
| Remote sensing and raster analysis | 75 | 83 |
| Climate and time series | 64 | 58 |
| GIS analysis | 92 | 90 |
Where the tasks are set: each kind of work links to its tasks and scoresCharts for each: DeepSeek V4.1 Flash (max), Claude Code · DeepSeek V4.1 Flash (max), Codex.
Side by side
| Metric | DeepSeek V4.1 Flash (max), Claude Code | DeepSeek V4.1 Flash (max), Codex |
|---|---|---|
| Geospatial Agent Index: Text only | 68 | 71 |
| Geospatial Agent Index: Text + vision | No data | 73 |
| Earth-Bench V2 score | 58 | 66 |
| GeoBenchX score | 55 | 56 |
| GS-QA2 score | 89 | 89 |
| Vision agents score | No data | 80 |
| GeoAgentBench score (Guided workflows; not in the Agent Index) | 96 | 90 |
| GeoAnalystBench score (Guided workflows; not in the Agent Index) | 100 | 88 |
| OGD4All score (standalone; in no index) | 79 | No data |
| GeoNatureAgent score (standalone; in no index) | 100 | No data |
| MultiGlobeQA score (standalone; in no index) | 64 | No data |
| GeoAgentEval score (standalone; in no index) | 84 | No data |
| Remote sensing and raster analysis score | 75 | 83 |
| GIS analysis score | 92 | 90 |
| Climate and time series score | 64 | 58 |
| Spatial statistics score | 31 | 46 |
| Making maps score | 72 | 72 |
| Recognising infeasible requests score | 40 | 41 |
| Cost per task | $0.20 | $0.067 |
| Time per task (at 100 output tokens/s) | 10.9 min | 8.6 min |
| Tokens per attempt | 1.58M | 1.17M |
| Turns per attempt | 26.0 | 23.4 |
| Input price per 1M tokens | $0.30 | $0.30 |
| Output price per 1M tokens | $1.20 | $1.20 |
| Context window | 1,048,576 | 1,048,576 |
| Image input | Yes | Yes |
| Developer | DeepSeek | DeepSeek |
Frequently asked questions
Which scores higher on the Geospatial Agent Index, DeepSeek V4.1 Flash (max), Claude Code or DeepSeek V4.1 Flash (max), Codex?
DeepSeek V4.1 Flash (max), Codex, 71 to 68.
Which is cheaper per task, DeepSeek V4.1 Flash (max), Claude Code or DeepSeek V4.1 Flash (max), Codex?
DeepSeek V4.1 Flash (max), Codex, $0.067 to $0.20.
Which writes fewer output tokens per task, DeepSeek V4.1 Flash (max), Claude Code or DeepSeek V4.1 Flash (max), Codex?
DeepSeek V4.1 Flash (max), Codex, 38k to 48k.
Which has the larger context window, DeepSeek V4.1 Flash (max), Claude Code or DeepSeek V4.1 Flash (max), Codex?
They are level, at 1,048,576 tokens.