Model comparison
Llama 3.1-405B vs Mistral Small 3.1
Mistral Small 3.1 is the stronger model overall, scoring 31.4 to 30.4 on the Noometry Index.
Last verified . 26 shared benchmarks.
Meta
Mistral AISummary
- They share 26 benchmarks with published results for both. Llama 3.1-405B scores higher in 4 categories and Mistral Small 3.1 in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 3.1-405B leads 30.4 to 22.6.
- The biggest single-benchmark swing is GPQA (HELM): 52.2% for Llama 3.1-405B and 39.2% for Mistral Small 3.1.
Side by side
| Llama 3.1-405B | Mistral Small 3.1 | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 30.4 | 31.4 |
| Released | 2024-07-23 | 2025-03-17 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 102K |
| Input $ / M tokens | — | $0.35 |
| Output $ / M tokens | — | $0.56 |
| Results tracked | 42 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3.1 leads
Llama 3.1-405B: 32.7 (#257), Mistral Small 3.1: 37.7 (#175)
| Benchmark | Llama 3.1-405B | Mistral Small 3.1 |
|---|---|---|
| LMArena Coding | 1291 | 1309 |
| WeirdML | 21.4% | — |
Agentic & Tool Use Not comparable
Llama 3.1-405B: 20.9 (#131), Mistral Small 3.1: —
| Benchmark | Llama 3.1-405B | Mistral Small 3.1 |
|---|---|---|
| TheAgentCompany | 7.4% | — |
| Cybench | 7.5% | — |
Reasoning Mistral Small 3.1 leads
Llama 3.1-405B: 16.4 (#293), Mistral Small 3.1: 18.9 (#249)
| Benchmark | Llama 3.1-405B | Mistral Small 3.1 |
|---|---|---|
| LMArena Hard Prompts | 1270 | 1278 |
| Epoch Capabilities Index | 128.76 | 127.48 |
| SimpleBench | 23% | — |
| Kagi LLM Benchmark | 45% | — |
| Chess Puzzles | — | 1% |
| DTBench | 61.4% | — |
| BIG-Bench Hard | 82.9% | — |
| ForecastBench | 59.9 | — |
| HellaSwag | 89.2% | — |
| PIQA | 85.9% | — |
| WinoGrande | 89.2% | — |
Math Llama 3.1-405B leads
Llama 3.1-405B: 17.3 (#283), Mistral Small 3.1: 13.7 (#295)
| Benchmark | Llama 3.1-405B | Mistral Small 3.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 9.7% | 3.9% |
| Omni-MATH | 24.9% | 24.8% |
| LMArena Math | 1281 | 1261 |
| MATH Level 5 | 49.8% | — |
Knowledge Llama 3.1-405B leads
Llama 3.1-405B: 30.4 (#221), Mistral Small 3.1: 22.6 (#266)
| Benchmark | Llama 3.1-405B | Mistral Small 3.1 |
|---|---|---|
| GPQA Diamond | 50.9% | 41.9% |
| MMLU-Pro | 72.3% | 61% |
| GPQA (HELM) | 52.2% | 39.2% |
| LMArena Expert | 1243 | 1258 |
| Confabulations | 17.6% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 84.5% | — |
| TriviaQA | 82.7% | — |
Multimodal Not comparable
Llama 3.1-405B: —, Mistral Small 3.1: 32.6 (#93)
| Benchmark | Llama 3.1-405B | Mistral Small 3.1 |
|---|---|---|
| LMArena Vision | — | 1136 |
Multilingual Too close to call
Llama 3.1-405B: 40.9 (#209), Mistral Small 3.1: 41.4 (#204)
| Benchmark | Llama 3.1-405B | Mistral Small 3.1 |
|---|---|---|
| LMArena Non-English | 1248 | 1255 |
| LMArena Chinese | 1242 | 1254 |
| LMArena French | 1278 | 1270 |
| LMArena German | 1252 | 1266 |
| LMArena Japanese | 1208 | 1210 |
| LMArena Korean | 1184 | 1206 |
| LMArena Russian | 1265 | 1263 |
| LMArena Spanish | 1259 | 1283 |
Instruction Following Llama 3.1-405B leads
Llama 3.1-405B: 66.1 (#209), Mistral Small 3.1: 63.8 (#225)
| Benchmark | Llama 3.1-405B | Mistral Small 3.1 |
|---|---|---|
| IFEval | 81.1% | 75% |
| LMArena Instruction Following | 1259 | 1264 |
Long Context Mistral Small 3.1 leads
Llama 3.1-405B: 38.4 (#192), Mistral Small 3.1: 39.5 (#172)
| Benchmark | Llama 3.1-405B | Mistral Small 3.1 |
|---|---|---|
| LMArena Longer Query | 1266 | 1300 |
Writing & Preference Llama 3.1-405B leads
Llama 3.1-405B: 39.1 (#246), Mistral Small 3.1: 37.2 (#254)
| Benchmark | Llama 3.1-405B | Mistral Small 3.1 |
|---|---|---|
| LMArena Text | 1284 | 1278 |
| LMArena Creative Writing | 1262 | 1253 |
| EQ-Bench Creative Writing | 870 | 761 |
| WildBench | 78.3% | 78.8% |
| LMArena Multi-Turn | 1297 | 1270 |
Frequently asked questions
Is Llama 3.1-405B better than Mistral Small 3.1?
Mistral Small 3.1 is the stronger model overall, scoring 31.4 to 30.4 on the Noometry Index.
Is Llama 3.1-405B or Mistral Small 3.1 better for coding?
Mistral Small 3.1 scores higher on coding benchmarks: 37.7 versus 32.7 in the Noometry coding category.
How many benchmarks do Llama 3.1-405B and Mistral Small 3.1 share?
26 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and Mistral Small 3.1 has 28.