Model comparison
DeepSeek V4 Pro vs Mistral Large 4
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 43.1 on the Noometry Index.
Last verified . 15 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 15 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 8 categories and Mistral Large 4 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Pro leads 56.5 to 22.5.
- The biggest single-benchmark swing is NYT Connections (extended): 91.3% for DeepSeek V4 Pro and 27.4% for Mistral Large 4.
- Both cost about the same: $0.66 input and $1.98 output per million tokens.
- Mistral Large 4 accepts more context: 1.05M tokens versus 1M.
- DeepSeek V4 Pro has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4 Pro | Mistral Large 4 | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 54.3 | 43.1 |
| Released | 2026-04-24 | 2026-10-06 |
| Weights | Open | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 393K | 262K |
| Input $ / M tokens | $0.66 | $0.68 |
| Output $ / M tokens | $1.98 | $2.09 |
| Results tracked | 48 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Pro leads
DeepSeek V4 Pro: 52.4 (#34), Mistral Large 4: 48.6 (#57)
| Benchmark | DeepSeek V4 Pro | Mistral Large 4 |
|---|---|---|
| LMArena WebDev | 1582 | 1541 |
| LMArena Coding | 1470 | 1475 |
| SWE-bench Verified | 77.6% | — |
| FrontierCode | 28.6% | — |
| SciCode | 51% | — |
| WeirdML | 66.2% | — |
| ALE-Bench | 1,403 | — |
Agentic & Tool Use Not comparable
DeepSeek V4 Pro: 32.8 (#58), Mistral Large 4: —
| Benchmark | DeepSeek V4 Pro | Mistral Large 4 |
|---|---|---|
| APEX-Agents | 47.3% | — |
| Vending-Bench 2 | 3,285 | — |
Reasoning DeepSeek V4 Pro leads
DeepSeek V4 Pro: 56.5 (#24), Mistral Large 4: 22.5 (#192)
| Benchmark | DeepSeek V4 Pro | Mistral Large 4 |
|---|---|---|
| NYT Connections (extended) | 91.3% | 27.4% |
| LMArena Hard Prompts | 1461 | 1444 |
| ARC-AGI-2 | 61.3% | — |
| Kagi LLM Benchmark | 53.5% | — |
| ARC-AGI-1 | 90.5% | — |
| CritPt | 18% | — |
| Chess Puzzles | 47% | — |
| Mystery Game Puzzles | 43% | — |
| DTBench | 93.9% | — |
| LMCA | 45.5% | — |
| Surface Evolver Bench | 40% | — |
| Epoch Capabilities Index | 155.31 | — |
| ForecastBench | 56.1 | — |
Math DeepSeek V4 Pro leads
DeepSeek V4 Pro: 64.8 (#30), Mistral Large 4: 40.4 (#91)
| Benchmark | DeepSeek V4 Pro | Mistral Large 4 |
|---|---|---|
| LMArena Math | 1455 | 1488 |
| FrontierMath (Tiers 1-3) | 64.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 76.6% | — |
| OTIS Mock AIME 2024-2025 | 98.6% | — |
| ProofBench | 50% | — |
Knowledge DeepSeek V4 Pro leads
DeepSeek V4 Pro: 59.5 (#31), Mistral Large 4: 36.6 (#166)
| Benchmark | DeepSeek V4 Pro | Mistral Large 4 |
|---|---|---|
| SimpleQA Verified | 52.9% | 20% |
| LMArena Expert | 1464 | 1447 |
| GPQA Diamond | 91.7% | — |
| Vectara Hallucination Rate | 8.6% | — |
Multilingual DeepSeek V4 Pro leads
DeepSeek V4 Pro: 54.4 (#45), Mistral Large 4: 52.6 (#82)
| Benchmark | DeepSeek V4 Pro | Mistral Large 4 |
|---|---|---|
| LMArena Non-English | 1439 | 1415 |
| LMArena Chinese | 1486 | 1491 |
| LMArena Russian | 1453 | 1414 |
| LMArena French | 1472 | — |
| LMArena German | 1458 | — |
| LMArena Japanese | 1445 | — |
| LMArena Korean | 1447 | — |
| LMArena Spanish | 1458 | — |
Instruction Following DeepSeek V4 Pro leads
DeepSeek V4 Pro: 76.1 (#47), Mistral Large 4: 75.0 (#76)
| Benchmark | DeepSeek V4 Pro | Mistral Large 4 |
|---|---|---|
| LMArena Instruction Following | 1448 | 1424 |
Long Context DeepSeek V4 Pro leads
DeepSeek V4 Pro: 45.0 (#51), Mistral Large 4: 43.6 (#89)
| Benchmark | DeepSeek V4 Pro | Mistral Large 4 |
|---|---|---|
| LMArena Longer Query | 1458 | 1429 |
| CL-bench Life | 13.5% | — |
Writing & Preference DeepSeek V4 Pro leads
DeepSeek V4 Pro: 65.5 (#46), Mistral Large 4: 60.4 (#97)
| Benchmark | DeepSeek V4 Pro | Mistral Large 4 |
|---|---|---|
| LMArena Text | 1451 | 1427 |
| LMArena Creative Writing | 1446 | 1361 |
| LMArena Multi-Turn | 1467 | 1424 |
| EQ-Bench Creative Writing | 1553 | — |
| EQ-Bench 4 | 1166 | — |
Frequently asked questions
Is DeepSeek V4 Pro better than Mistral Large 4?
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 43.1 on the Noometry Index.
Which is cheaper, DeepSeek V4 Pro or Mistral Large 4?
DeepSeek V4 Pro is cheaper. It lists at $0.66 per million input tokens and $1.98 per million output tokens; Mistral Large 4 lists at $0.68 and $2.09.
Is DeepSeek V4 Pro or Mistral Large 4 better for coding?
DeepSeek V4 Pro scores higher on coding benchmarks: 52.4 versus 48.6 in the Noometry coding category.
Which has the bigger context window?
Mistral Large 4 does, with 1.05M tokens against 1M.
How many benchmarks do DeepSeek V4 Pro and Mistral Large 4 share?
15 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and Mistral Large 4 has 15.