Model comparison
Llama 3.1-405B vs Mistral Large
Mistral Large is the stronger model overall, scoring 31.9 to 30.7 on the Noometry Index.
Last verified . 32 shared benchmarks.
Meta
Mistral AISummary
- They share 32 benchmarks with published results for both. Llama 3.1-405B scores higher in 5 categories and Mistral Large in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Mistral Large leads 28.6 to 21.0.
- The biggest single-benchmark swing is MMLU-Pro: 72.3% for Llama 3.1-405B and 59.9% for Mistral Large.
Side by side
| Llama 3.1-405B | Mistral Large | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 30.7 | 31.9 |
| Released | 2024-07-23 | 2024-02-26 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 42 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large leads
Llama 3.1-405B: 33.1 (#262), Mistral Large: 34.3 (#240)
| Benchmark | Llama 3.1-405B | Mistral Large |
|---|---|---|
| LMArena Coding | 1291 | 1277 |
| SciCode | — | 36.2% |
| WeirdML | 21.4% | — |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| ALE-Bench | — | 264.7 |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use Mistral Large leads
Llama 3.1-405B: 21.0 (#140), Mistral Large: 28.6 (#89)
| Benchmark | Llama 3.1-405B | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 38.4% |
| TheAgentCompany | 7.4% | — |
| Cybench | 7.5% | — |
Reasoning Llama 3.1-405B leads
Llama 3.1-405B: 16.8 (#300), Mistral Large: 15.8 (#310)
| Benchmark | Llama 3.1-405B | Mistral Large |
|---|---|---|
| SimpleBench | 23% | 22.5% |
| LMArena Hard Prompts | 1269 | 1257 |
| DTBench | 61.4% | 65.1% |
| Epoch Capabilities Index | 128.75 | 128.52 |
| ForecastBench | 59.9 | 57.1 |
| Kagi LLM Benchmark | 45% | — |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 43.5% |
| LiveBench Data Analysis | — | 50.1% |
| LMCA | — | 16.7% |
| BIG-Bench Hard | 82.9% | — |
| HellaSwag | 89.2% | — |
| LiveBench | — | 48.4% |
| PIQA | 85.9% | — |
| WinoGrande | 89.2% | — |
Math Too close to call
Llama 3.1-405B: 18.4 (#290), Mistral Large: 18.2 (#291)
| Benchmark | Llama 3.1-405B | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 9.7% | 8.5% |
| Omni-MATH | 24.9% | 28.1% |
| LMArena Math | 1281 | 1262 |
| MATH Level 5 | 49.8% | 50.3% |
| LiveBench Math | — | 42.5% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Too close to call
Llama 3.1-405B: 30.4 (#227), Mistral Large: 30.1 (#230)
| Benchmark | Llama 3.1-405B | Mistral Large |
|---|---|---|
| GPQA Diamond | 50.9% | 51.3% |
| MMLU-Pro | 72.3% | 59.9% |
| Confabulations | 17.6% | 21.4% |
| GPQA (HELM) | 52.2% | 43.5% |
| LMArena Expert | 1243 | 1232 |
| MMLU | 84.5% | 80% |
| Vectara Hallucination Rate | — | 4.5% |
| ARC (AI2) Challenge | 95.3% | — |
| TriviaQA | 82.7% | — |
Multilingual Too close to call
Llama 3.1-405B: 40.7 (#214), Mistral Large: 40.0 (#219)
| Benchmark | Llama 3.1-405B | Mistral Large |
|---|---|---|
| LMArena Non-English | 1248 | 1237 |
| LMArena Chinese | 1242 | 1240 |
| LMArena French | 1279 | 1325 |
| LMArena German | 1252 | 1254 |
| LMArena Japanese | 1208 | 1188 |
| LMArena Korean | 1184 | 1202 |
| LMArena Russian | 1265 | 1257 |
| LMArena Spanish | 1260 | 1268 |
Instruction Following Mistral Large leads
Llama 3.1-405B: 65.9 (#214), Mistral Large: 67.9 (#191)
| Benchmark | Llama 3.1-405B | Mistral Large |
|---|---|---|
| IFEval | 81.1% | 87.7% |
| LMArena Instruction Following | 1259 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
Long Context Too close to call
Llama 3.1-405B: 38.4 (#197), Mistral Large: 38.3 (#199)
| Benchmark | Llama 3.1-405B | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1266 | 1261 |
Writing & Preference Mistral Large leads
Llama 3.1-405B: 38.9 (#251), Mistral Large: 40.7 (#242)
| Benchmark | Llama 3.1-405B | Mistral Large |
|---|---|---|
| LMArena Text | 1284 | 1266 |
| LMArena Creative Writing | 1262 | 1243 |
| EQ-Bench Creative Writing | 870 | 985 |
| WildBench | 78.3% | 80.1% |
| LMArena Multi-Turn | 1297 | 1260 |
| Short-Story Creative Writing | — | 69% |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is Llama 3.1-405B better than Mistral Large?
Mistral Large is the stronger model overall, scoring 31.9 to 30.7 on the Noometry Index.
Is Llama 3.1-405B or Mistral Large better for coding?
Mistral Large scores higher on coding benchmarks: 34.3 versus 33.1 in the Noometry coding category.
How many benchmarks do Llama 3.1-405B and Mistral Large share?
32 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and Mistral Large has 51.