DeepSeek V4 Flash (high) vs MiniMax M3 (Reasoning)
Results updated 1 November 2026 · In Codex and MiniMax Code, so part of any gap can come from the harness · How we benchmark
Verdict
MiniMax M3 (Reasoning) edges DeepSeek V4 Flash (high) by 2 points, and is faster; DeepSeek V4 Flash (high) is cheaper.
- Cost per task
- $0.085 vs $0.15
- Time per task
- 6.5 min vs 4.9 min (estimated)
- Tokens per attempt
- 1.13M vs 1.68M
- Image input
- No vs Yes
DeepSeek V4 Flash (high), Codex scores higher on Earth-Bench V2; MiniMax M3 (Reasoning), MiniMax Code scores higher on GeoBenchX and GS-QA2. DeepSeek V4 Flash (high), Codex is cheaper ($0.085 against $0.15 per task), but MiniMax M3 (Reasoning), MiniMax Code is faster (4.9 min against 6.5 min).
Where they differ most
By kind of work, share of tasks passed, 0 to 100 · Higher is better
| Kind of work | DeepSeek V4 Flash (high) | MiniMax M3 (Reasoning) |
|---|---|---|
| Spatial statistics | 42 | 62 |
| Making maps | 70 | 77 |
| GIS analysis | 75 | 81 |
| Recognising infeasible requests | 37 | 33 |
Where the tasks are set: each kind of work links to its tasks and scoresCharts for each: DeepSeek V4 Flash (high), Codex · MiniMax M3 (Reasoning), MiniMax Code.
Side by side
| Metric | DeepSeek V4 Flash (high), Codex | MiniMax M3 (Reasoning), MiniMax Code |
|---|---|---|
| Geospatial Agent Index: Text only | 66 | 68 |
| Geospatial Agent Index: Text + vision | No image input | No data |
| Earth-Bench V2 score | 70 | 68 |
| GeoBenchX score | 54 | 59 |
| GS-QA2 score | 74 | 78 |
| Vision agents score | No image input | No data |
| GeoAgentBench score (Guided workflows; not in the Agent Index) | 92 | 94 |
| GeoAnalystBench score (Guided workflows; not in the Agent Index) | 89 | 79 |
| OGD4All score (standalone; in no index) | No data | 94 |
| GeoNatureAgent score (standalone; in no index) | No data | 93 |
| MultiGlobeQA score (standalone; in no index) | No data | 73 |
| GeoAgentEval score (standalone; in no index) | No data | 92 |
| ImpactMesh score (standalone; in no index) | No data | No data |
| Remote sensing and raster analysis score | 72 | 73 |
| GIS analysis score | 75 | 81 |
| Climate and time series score | 73 | 74 |
| Spatial statistics score | 42 | 62 |
| Making maps score | 70 | 77 |
| Recognising infeasible requests score | 37 | 33 |
| Cost per task | $0.085 | $0.15 |
| Time per task (at 100 output tokens/s) | 6.5 min | 4.9 min (estimated) |
| Tokens per attempt | 1.13M | 1.68M |
| Turns per attempt | 25.4 | No data |
| Input price per 1M tokens | $0.44 | $0.30 |
| Output price per 1M tokens | $1.32 | $1.20 |
| Context window | 1,048,576 | 1,048,576 |
| Image input | No | Yes |
| Developer | DeepSeek | MiniMax |
Frequently asked questions
Which scores higher on the Geospatial Agent Index, DeepSeek V4 Flash (high), Codex or MiniMax M3 (Reasoning), MiniMax Code?
MiniMax M3 (Reasoning), MiniMax Code, 68 to 66.
Which is cheaper per task, DeepSeek V4 Flash (high), Codex or MiniMax M3 (Reasoning), MiniMax Code?
DeepSeek V4 Flash (high), Codex, $0.085 to $0.15.
Which writes fewer output tokens per task, DeepSeek V4 Flash (high), Codex or MiniMax M3 (Reasoning), MiniMax Code?
DeepSeek V4 Flash (high), Codex, 19k to 29k.
Which has the larger context window, DeepSeek V4 Flash (high), Codex or MiniMax M3 (Reasoning), MiniMax Code?
They are level, at 1,048,576 tokens.