Model comparison
DeepSeek-V3.1 vs Mistral Large 4
DeepSeek-V3.1 and Mistral Large 4 score almost the same on the Noometry Index (42.8 vs 43.1), so choose on price, context window or the category you care about most.
Last verified . 12 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 12 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 2 categories and Mistral Large 4 in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Mistral Large 4 leads 48.6 to 40.3.
- DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $0.68 / $2.09 for Mistral Large 4.
- Mistral Large 4 accepts more context: 1.05M tokens versus 164K.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1 | Mistral Large 4 | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 42.8 | 43.1 |
| Released | 2025-08-21 | 2026-10-06 |
| Weights | Open | Proprietary |
| Context window | 164K | 1.05M |
| Max output | 8K | 262K |
| Input $ / M tokens | $0.25 | $0.68 |
| Output $ / M tokens | $0.95 | $2.09 |
| Results tracked | 27 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large 4 leads
DeepSeek-V3.1: 40.3 (#144), Mistral Large 4: 48.6 (#57)
| Benchmark | DeepSeek-V3.1 | Mistral Large 4 |
|---|---|---|
| LMArena Coding | 1417 | 1475 |
| LMArena WebDev | — | 1541 |
| WeirdML | 38.4% | — |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.9 (#110), Mistral Large 4: 22.5 (#192)
| Benchmark | DeepSeek-V3.1 | Mistral Large 4 |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1444 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| NYT Connections (extended) | — | 27.4% |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| Epoch Capabilities Index | 139.92 | — |
| ForecastBench | 58 | — |
Math Mistral Large 4 leads
DeepSeek-V3.1: 38.9 (#122), Mistral Large 4: 40.4 (#91)
| Benchmark | DeepSeek-V3.1 | Mistral Large 4 |
|---|---|---|
| LMArena Math | 1420 | 1488 |
Knowledge DeepSeek-V3.1 leads
DeepSeek-V3.1: 43.7 (#90), Mistral Large 4: 36.6 (#166)
| Benchmark | DeepSeek-V3.1 | Mistral Large 4 |
|---|---|---|
| LMArena Expert | 1405 | 1447 |
| SimpleQA Verified | — | 20% |
| Vectara Hallucination Rate | 5.5% | — |
Multilingual Mistral Large 4 leads
DeepSeek-V3.1: 51.6 (#106), Mistral Large 4: 52.6 (#82)
| Benchmark | DeepSeek-V3.1 | Mistral Large 4 |
|---|---|---|
| LMArena Non-English | 1400 | 1415 |
| LMArena Chinese | 1469 | 1491 |
| LMArena Russian | 1405 | 1414 |
| LMArena French | 1447 | — |
| LMArena German | 1411 | — |
| LMArena Japanese | 1378 | — |
| LMArena Korean | 1337 | — |
| LMArena Spanish | 1431 | — |
Instruction Following Mistral Large 4 leads
DeepSeek-V3.1: 73.9 (#110), Mistral Large 4: 75.0 (#76)
| Benchmark | DeepSeek-V3.1 | Mistral Large 4 |
|---|---|---|
| LMArena Instruction Following | 1400 | 1424 |
Long Context Mistral Large 4 leads
DeepSeek-V3.1: 36.3 (#232), Mistral Large 4: 43.6 (#89)
| Benchmark | DeepSeek-V3.1 | Mistral Large 4 |
|---|---|---|
| LMArena Longer Query | 1422 | 1429 |
| Fiction.LiveBench | 52.8% | — |
Writing & Preference Too close to call
DeepSeek-V3.1: 60.3 (#98), Mistral Large 4: 60.4 (#97)
| Benchmark | DeepSeek-V3.1 | Mistral Large 4 |
|---|---|---|
| LMArena Text | 1420 | 1427 |
| LMArena Creative Writing | 1401 | 1361 |
| LMArena Multi-Turn | 1408 | 1424 |
| EQ-Bench Creative Writing | 1436 | — |
Frequently asked questions
Is DeepSeek-V3.1 better than Mistral Large 4?
DeepSeek-V3.1 and Mistral Large 4 score almost the same on the Noometry Index (42.8 vs 43.1), so choose on price, context window or the category you care about most.
Which is cheaper, DeepSeek-V3.1 or Mistral Large 4?
DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; Mistral Large 4 lists at $0.68 and $2.09.
Is DeepSeek-V3.1 or Mistral Large 4 better for coding?
Mistral Large 4 scores higher on coding benchmarks: 48.6 versus 40.3 in the Noometry coding category.
Which has the bigger context window?
Mistral Large 4 does, with 1.05M tokens against 164K.
How many benchmarks do DeepSeek-V3.1 and Mistral Large 4 share?
12 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Mistral Large 4 has 15.