Model comparison
DeepSeek V4 Pro vs Mistral Small 3.1
DeepSeek V4 Pro is the stronger model overall, scoring 54.2 to 31.4 on the Noometry Index.
Last verified . 22 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 22 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 8 categories and Mistral Small 3.1 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4 Pro leads 64.6 to 13.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.6% for DeepSeek V4 Pro and 3.9% for Mistral Small 3.1.
- Mistral Small 3.1 is cheaper at $0.35 / $0.56 per million input/output tokens, against $0.43 / $0.87 for DeepSeek V4 Pro.
- DeepSeek V4 Pro accepts more context: 1M tokens versus 128K.
Side by side
| DeepSeek V4 Pro | Mistral Small 3.1 | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 54.2 | 31.4 |
| Released | 2026-04-24 | 2025-03-17 |
| Weights | Open | Open |
| Context window | 1M | 128K |
| Max output | 393K | 102K |
| Input $ / M tokens | $0.43 | $0.35 |
| Output $ / M tokens | $0.87 | $0.56 |
| Results tracked | 48 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Pro leads
DeepSeek V4 Pro: 52.2 (#31), Mistral Small 3.1: 37.7 (#175)
| Benchmark | DeepSeek V4 Pro | Mistral Small 3.1 |
|---|---|---|
| LMArena Coding | 1470 | 1309 |
| SWE-bench Verified | 77.6% | — |
| FrontierCode | 28.6% | — |
| LMArena WebDev | 1582 | — |
| SciCode | 51% | — |
| WeirdML | 66.2% | — |
| ALE-Bench | 1,403 | — |
Agentic & Tool Use Not comparable
DeepSeek V4 Pro: 32.7 (#54), Mistral Small 3.1: —
| Benchmark | DeepSeek V4 Pro | Mistral Small 3.1 |
|---|---|---|
| APEX-Agents | 47.3% | — |
| Vending-Bench 2 | 3,285 | — |
Reasoning DeepSeek V4 Pro leads
DeepSeek V4 Pro: 56.4 (#22), Mistral Small 3.1: 18.9 (#249)
| Benchmark | DeepSeek V4 Pro | Mistral Small 3.1 |
|---|---|---|
| Chess Puzzles | 47% | 1% |
| LMArena Hard Prompts | 1461 | 1278 |
| Epoch Capabilities Index | 155.39 | 127.48 |
| ARC-AGI-2 | 61.3% | — |
| Kagi LLM Benchmark | 53.5% | — |
| NYT Connections (extended) | 91.3% | — |
| ARC-AGI-1 | 90.5% | — |
| CritPt | 18% | — |
| Mystery Game Puzzles | 43% | — |
| DTBench | 93.9% | — |
| LMCA | 45.5% | — |
| Surface Evolver Bench | 40% | — |
| ForecastBench | 56.1 | — |
Math DeepSeek V4 Pro leads
DeepSeek V4 Pro: 64.6 (#24), Mistral Small 3.1: 13.7 (#295)
| Benchmark | DeepSeek V4 Pro | Mistral Small 3.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.6% | 3.9% |
| LMArena Math | 1455 | 1261 |
| FrontierMath (Tiers 1-3) | 64.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 76.6% | — |
| ProofBench | 50% | — |
| Omni-MATH | — | 24.8% |
Knowledge DeepSeek V4 Pro leads
DeepSeek V4 Pro: 59.5 (#28), Mistral Small 3.1: 22.6 (#266)
| Benchmark | DeepSeek V4 Pro | Mistral Small 3.1 |
|---|---|---|
| GPQA Diamond | 91.7% | 41.9% |
| LMArena Expert | 1463 | 1258 |
| SimpleQA Verified | 52.9% | — |
| MMLU-Pro | — | 61% |
| Vectara Hallucination Rate | 8.6% | — |
| GPQA (HELM) | — | 39.2% |
Multimodal Not comparable
DeepSeek V4 Pro: —, Mistral Small 3.1: 32.6 (#93)
| Benchmark | DeepSeek V4 Pro | Mistral Small 3.1 |
|---|---|---|
| LMArena Vision | — | 1136 |
Multilingual DeepSeek V4 Pro leads
DeepSeek V4 Pro: 54.5 (#44), Mistral Small 3.1: 41.4 (#204)
| Benchmark | DeepSeek V4 Pro | Mistral Small 3.1 |
|---|---|---|
| LMArena Non-English | 1438 | 1255 |
| LMArena Chinese | 1486 | 1254 |
| LMArena French | 1473 | 1270 |
| LMArena German | 1458 | 1266 |
| LMArena Japanese | 1448 | 1210 |
| LMArena Korean | 1452 | 1206 |
| LMArena Russian | 1452 | 1263 |
| LMArena Spanish | 1457 | 1283 |
Instruction Following DeepSeek V4 Pro leads
DeepSeek V4 Pro: 76.3 (#44), Mistral Small 3.1: 63.8 (#225)
| Benchmark | DeepSeek V4 Pro | Mistral Small 3.1 |
|---|---|---|
| LMArena Instruction Following | 1448 | 1264 |
| IFEval | — | 75% |
Long Context DeepSeek V4 Pro leads
DeepSeek V4 Pro: 45.0 (#49), Mistral Small 3.1: 39.5 (#172)
| Benchmark | DeepSeek V4 Pro | Mistral Small 3.1 |
|---|---|---|
| LMArena Longer Query | 1459 | 1300 |
| CL-bench Life | 13.5% | — |
Writing & Preference DeepSeek V4 Pro leads
DeepSeek V4 Pro: 65.6 (#45), Mistral Small 3.1: 37.2 (#254)
| Benchmark | DeepSeek V4 Pro | Mistral Small 3.1 |
|---|---|---|
| LMArena Text | 1451 | 1278 |
| LMArena Creative Writing | 1446 | 1253 |
| EQ-Bench Creative Writing | 1553 | 761 |
| LMArena Multi-Turn | 1467 | 1270 |
| WildBench | — | 78.8% |
| EQ-Bench 4 | 1166 | — |
Frequently asked questions
Is DeepSeek V4 Pro better than Mistral Small 3.1?
DeepSeek V4 Pro is the stronger model overall, scoring 54.2 to 31.4 on the Noometry Index.
Which is cheaper, DeepSeek V4 Pro or Mistral Small 3.1?
Mistral Small 3.1 is cheaper. It lists at $0.35 per million input tokens and $0.56 per million output tokens; DeepSeek V4 Pro lists at $0.43 and $0.87.
Is DeepSeek V4 Pro or Mistral Small 3.1 better for coding?
DeepSeek V4 Pro scores higher on coding benchmarks: 52.2 versus 37.7 in the Noometry coding category.
Which has the bigger context window?
DeepSeek V4 Pro does, with 1M tokens against 128K.
How many benchmarks do DeepSeek V4 Pro and Mistral Small 3.1 share?
22 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and Mistral Small 3.1 has 28.