Model comparison
DeepSeek-V3 vs Mistral Large 3
DeepSeek-V3 and Mistral Large 3 score almost the same on the Noometry Index (39.5 vs 39.1), so choose on price, context window or the category you care about most.
Last verified . 20 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 20 benchmarks with published results for both. DeepSeek-V3 scores higher in 3 categories and Mistral Large 3 in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where Mistral Large 3 leads 43.1 to 34.0.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 6.1% for DeepSeek-V3 and 14.5% for Mistral Large 3.
- Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.24 / $0.90 for DeepSeek-V3.
- Mistral Large 3 accepts more context: 262K tokens versus 164K.
Side by side
| DeepSeek-V3 | Mistral Large 3 | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 39.5 | 39.1 |
| Released | 2024-12-26 | 2025-12-02 |
| Weights | Open | Open |
| Context window | 164K | 262K |
| Max output | 164K | 8K |
| Input $ / M tokens | $0.24 | $0.25 |
| Output $ / M tokens | $0.90 | $0.75 |
| Results tracked | 60 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3 leads
DeepSeek-V3: 42.3 (#106), Mistral Large 3: 34.4 (#237)
| Benchmark | DeepSeek-V3 | Mistral Large 3 |
|---|---|---|
| LMArena Coding | 1368 | 1448 |
| Aider Polyglot | 55.1% | — |
| LMArena WebDev | — | 1230 |
| SciCode | 35.8% | — |
| WeirdML | 36.1% | — |
| BigCodeBench Instruct | 50% | — |
| LiveBench Coding | 70.9% | — |
| BigCodeBench Complete | 62.2% | — |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73% | — |
Agentic & Tool Use Not comparable
DeepSeek-V3: —, Mistral Large 3: —
| Benchmark | DeepSeek-V3 | Mistral Large 3 |
|---|---|---|
| METR Time Horizons | 49.6% | — |
Reasoning DeepSeek-V3 leads
DeepSeek-V3: 20.5 (#236), Mistral Large 3: 15.2 (#319)
| Benchmark | DeepSeek-V3 | Mistral Large 3 |
|---|---|---|
| Kagi LLM Benchmark | 52.3% | 50.9% |
| LMArena Hard Prompts | 1365 | 1429 |
| SimpleBench | 27.2% | — |
| NYT Connections (extended) | — | 7.5% |
| CritPt | 0% | — |
| Thematic Generalization | — | 23% |
| LiveBench Reasoning | 65.8% | — |
| DTBench | 64.8% | — |
| LiveBench Data Analysis | 60.9% | — |
| LMCA | 15.5% | — |
| BIG-Bench Hard | 87.5% | — |
| Epoch Capabilities Index | 135.94 | — |
| ForecastBench | 59.1 | — |
| HellaSwag | 88.9% | — |
| LiveBench | 66.9% | — |
| PIQA | 84.7% | — |
| WinoGrande | 85.2% | — |
Math Mistral Large 3 leads
DeepSeek-V3: 32.1 (#219), Mistral Large 3: 38.7 (#129)
| Benchmark | DeepSeek-V3 | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1373 | 1414 |
| OTIS Mock AIME 2024-2025 | 37.8% | — |
| Omni-MATH | 40.3% | — |
| LiveBench Math | 73.5% | — |
| MATH Level 5 | 75.5% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge DeepSeek-V3 leads
DeepSeek-V3: 37.5 (#155), Mistral Large 3: 36.0 (#177)
| Benchmark | DeepSeek-V3 | Mistral Large 3 |
|---|---|---|
| Vectara Hallucination Rate | 6.1% | 14.5% |
| LMArena Expert | 1351 | 1421 |
| GPQA Diamond | 67.6% | — |
| MMLU-Pro | 72.3% | — |
| Confabulations | 26.1% | — |
| GPQA (HELM) | 53.8% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 87.2% | — |
| TriviaQA | 82.9% | — |
Multimodal Not comparable
DeepSeek-V3: —, Mistral Large 3: 38.2 (#66)
| Benchmark | DeepSeek-V3 | Mistral Large 3 |
|---|---|---|
| LMArena Vision | — | 1221 |
Multilingual Mistral Large 3 leads
DeepSeek-V3: 48.5 (#143), Mistral Large 3: 52.5 (#84)
| Benchmark | DeepSeek-V3 | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1358 | 1413 |
| LMArena Chinese | 1391 | 1447 |
| LMArena French | 1385 | 1455 |
| LMArena German | 1374 | 1437 |
| LMArena Japanese | 1333 | 1394 |
| LMArena Korean | 1319 | 1384 |
| LMArena Russian | 1373 | 1411 |
| LMArena Spanish | 1358 | 1440 |
Instruction Following Mistral Large 3 leads
DeepSeek-V3: 72.8 (#130), Mistral Large 3: 74.0 (#108)
| Benchmark | DeepSeek-V3 | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1345 | 1403 |
| LiveBench Instruction Following | 81.5% | — |
| IFEval | 83.2% | — |
Long Context Mistral Large 3 leads
DeepSeek-V3: 34.0 (#253), Mistral Large 3: 43.1 (#105)
| Benchmark | DeepSeek-V3 | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1352 | 1413 |
| Fiction.LiveBench | 50% | — |
Writing & Preference Mistral Large 3 leads
DeepSeek-V3: 57.4 (#130), Mistral Large 3: 60.0 (#101)
| Benchmark | DeepSeek-V3 | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1375 | 1428 |
| LMArena Creative Writing | 1364 | 1386 |
| EQ-Bench Creative Writing | 1472 | 1412 |
| LMArena Multi-Turn | 1389 | 1429 |
| Short-Story Creative Writing | 77% | — |
| WildBench | 83% | — |
| LiveBench Language | 49.1% | — |
Frequently asked questions
Is DeepSeek-V3 better than Mistral Large 3?
DeepSeek-V3 and Mistral Large 3 score almost the same on the Noometry Index (39.5 vs 39.1), so choose on price, context window or the category you care about most.
Which is cheaper, DeepSeek-V3 or Mistral Large 3?
Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; DeepSeek-V3 lists at $0.24 and $0.90.
Is DeepSeek-V3 or Mistral Large 3 better for coding?
DeepSeek-V3 scores higher on coding benchmarks: 42.3 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
Mistral Large 3 does, with 262K tokens against 164K.
How many benchmarks do DeepSeek-V3 and Mistral Large 3 share?
20 benchmarks have published results for both models. DeepSeek-V3 has 60 scored results on Noometry and Mistral Large 3 has 24.