Model comparison
Llama 3.1-405B vs Mistral Large 3
Mistral Large 3 is the stronger model overall, scoring 39.1 to 30.7 on the Noometry Index.
Last verified . 19 shared benchmarks.
Meta
Mistral AISummary
- They share 19 benchmarks with published results for both. Llama 3.1-405B scores higher in 1 category and Mistral Large 3 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Large 3 leads 60.0 to 38.9.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 45% for Llama 3.1-405B and 50.9% for Mistral Large 3.
Side by side
| Llama 3.1-405B | Mistral Large 3 | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 30.7 | 39.1 |
| Released | 2024-07-23 | 2025-12-02 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.75 |
| Results tracked | 42 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large 3 leads
Llama 3.1-405B: 33.1 (#262), Mistral Large 3: 34.4 (#237)
| Benchmark | Llama 3.1-405B | Mistral Large 3 |
|---|---|---|
| LMArena Coding | 1291 | 1448 |
| LMArena WebDev | — | 1230 |
| WeirdML | 21.4% | — |
Agentic & Tool Use Not comparable
Llama 3.1-405B: 21.0 (#140), Mistral Large 3: —
| Benchmark | Llama 3.1-405B | Mistral Large 3 |
|---|---|---|
| TheAgentCompany | 7.4% | — |
| Cybench | 7.5% | — |
Reasoning Llama 3.1-405B leads
Llama 3.1-405B: 16.8 (#300), Mistral Large 3: 15.2 (#319)
| Benchmark | Llama 3.1-405B | Mistral Large 3 |
|---|---|---|
| Kagi LLM Benchmark | 45% | 50.9% |
| LMArena Hard Prompts | 1269 | 1429 |
| SimpleBench | 23% | — |
| NYT Connections (extended) | — | 7.5% |
| Thematic Generalization | — | 23% |
| DTBench | 61.4% | — |
| BIG-Bench Hard | 82.9% | — |
| Epoch Capabilities Index | 128.75 | — |
| ForecastBench | 59.9 | — |
| HellaSwag | 89.2% | — |
| PIQA | 85.9% | — |
| WinoGrande | 89.2% | — |
Math Mistral Large 3 leads
Llama 3.1-405B: 18.4 (#290), Mistral Large 3: 38.7 (#129)
| Benchmark | Llama 3.1-405B | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1281 | 1414 |
| OTIS Mock AIME 2024-2025 | 9.7% | — |
| Omni-MATH | 24.9% | — |
| MATH Level 5 | 49.8% | — |
Knowledge Mistral Large 3 leads
Llama 3.1-405B: 30.4 (#227), Mistral Large 3: 36.0 (#177)
| Benchmark | Llama 3.1-405B | Mistral Large 3 |
|---|---|---|
| LMArena Expert | 1243 | 1421 |
| GPQA Diamond | 50.9% | — |
| MMLU-Pro | 72.3% | — |
| Confabulations | 17.6% | — |
| Vectara Hallucination Rate | — | 14.5% |
| GPQA (HELM) | 52.2% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 84.5% | — |
| TriviaQA | 82.7% | — |
Multimodal Not comparable
Llama 3.1-405B: —, Mistral Large 3: 38.2 (#66)
| Benchmark | Llama 3.1-405B | Mistral Large 3 |
|---|---|---|
| LMArena Vision | — | 1221 |
Multilingual Mistral Large 3 leads
Llama 3.1-405B: 40.7 (#214), Mistral Large 3: 52.5 (#84)
| Benchmark | Llama 3.1-405B | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1248 | 1413 |
| LMArena Chinese | 1242 | 1447 |
| LMArena French | 1279 | 1455 |
| LMArena German | 1252 | 1437 |
| LMArena Japanese | 1208 | 1394 |
| LMArena Korean | 1184 | 1384 |
| LMArena Russian | 1265 | 1411 |
| LMArena Spanish | 1260 | 1440 |
Instruction Following Mistral Large 3 leads
Llama 3.1-405B: 65.9 (#214), Mistral Large 3: 74.0 (#108)
| Benchmark | Llama 3.1-405B | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1259 | 1403 |
| IFEval | 81.1% | — |
Long Context Mistral Large 3 leads
Llama 3.1-405B: 38.4 (#197), Mistral Large 3: 43.1 (#105)
| Benchmark | Llama 3.1-405B | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1266 | 1413 |
Writing & Preference Mistral Large 3 leads
Llama 3.1-405B: 38.9 (#251), Mistral Large 3: 60.0 (#101)
| Benchmark | Llama 3.1-405B | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1284 | 1428 |
| LMArena Creative Writing | 1262 | 1386 |
| EQ-Bench Creative Writing | 870 | 1412 |
| LMArena Multi-Turn | 1297 | 1429 |
| WildBench | 78.3% | — |
Frequently asked questions
Is Llama 3.1-405B better than Mistral Large 3?
Mistral Large 3 is the stronger model overall, scoring 39.1 to 30.7 on the Noometry Index.
Is Llama 3.1-405B or Mistral Large 3 better for coding?
Mistral Large 3 scores higher on coding benchmarks: 34.4 versus 33.1 in the Noometry coding category.
How many benchmarks do Llama 3.1-405B and Mistral Large 3 share?
19 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and Mistral Large 3 has 24.