Model comparison
Llama 3.1-405B vs Mistral Nemo
Llama 3.1-405B is the stronger model overall, scoring 30.7 to 26.4 on the Noometry Index.
Last verified . 6 shared benchmarks.
Meta
Mistral AISummary
- They share 6 benchmarks with published results for both. Llama 3.1-405B scores higher in 2 categories and Mistral Nemo in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 3.1-405B leads 30.4 to 12.3.
- The biggest single-benchmark swing is MATH Level 5: 49.8% for Llama 3.1-405B and 10.8% for Mistral Nemo.
Side by side
| Llama 3.1-405B | Mistral Nemo | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 30.7 | 26.4 |
| Released | 2024-07-23 | 2024-07-01 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.15 |
| Results tracked | 42 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.1-405B: 33.1 (#262), Mistral Nemo: —
| Benchmark | Llama 3.1-405B | Mistral Nemo |
|---|---|---|
| WeirdML | 21.4% | — |
| LMArena Coding | 1291 | — |
Agentic & Tool Use Mistral Nemo leads
Llama 3.1-405B: 21.0 (#140), Mistral Nemo: 23.5 (#125)
| Benchmark | Llama 3.1-405B | Mistral Nemo |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 27.6% |
| TheAgentCompany | 7.4% | — |
| Cybench | 7.5% | — |
| BALROG | — | 17.6% |
Reasoning Mistral Nemo leads
Llama 3.1-405B: 16.8 (#300), Mistral Nemo: 20.7 (#232)
| Benchmark | Llama 3.1-405B | Mistral Nemo |
|---|---|---|
| DTBench | 61.4% | 48.6% |
| Epoch Capabilities Index | 128.75 | 118.68 |
| PIQA | 85.9% | 83.5% |
| SimpleBench | 23% | — |
| Kagi LLM Benchmark | 45% | — |
| LMArena Hard Prompts | 1269 | — |
| BIG-Bench Hard | 82.9% | — |
| ForecastBench | 59.9 | — |
| HellaSwag | 89.2% | — |
| WinoGrande | 89.2% | — |
Math Mistral Nemo leads
Llama 3.1-405B: 18.4 (#290), Mistral Nemo: 25.5 (#268)
| Benchmark | Llama 3.1-405B | Mistral Nemo |
|---|---|---|
| MATH Level 5 | 49.8% | 10.8% |
| OTIS Mock AIME 2024-2025 | 9.7% | — |
| Omni-MATH | 24.9% | — |
| LMArena Math | 1281 | — |
| GSM8K | — | 84.2% |
Knowledge Llama 3.1-405B leads
Llama 3.1-405B: 30.4 (#227), Mistral Nemo: 12.3 (#298)
| Benchmark | Llama 3.1-405B | Mistral Nemo |
|---|---|---|
| GPQA Diamond | 50.9% | 29.9% |
| MMLU-Pro | 72.3% | — |
| Confabulations | 17.6% | — |
| GPQA (HELM) | 52.2% | — |
| LMArena Expert | 1243 | — |
| ARC (AI2) Challenge | 95.3% | — |
| BoolQ | — | 82.5% |
| MMLU | 84.5% | — |
| TriviaQA | 82.7% | — |
Multilingual Not comparable
Llama 3.1-405B: 40.7 (#214), Mistral Nemo: —
| Benchmark | Llama 3.1-405B | Mistral Nemo |
|---|---|---|
| LMArena Non-English | 1248 | — |
| LMArena Chinese | 1242 | — |
| LMArena French | 1279 | — |
| LMArena German | 1252 | — |
| LMArena Japanese | 1208 | — |
| LMArena Korean | 1184 | — |
| LMArena Russian | 1265 | — |
| LMArena Spanish | 1260 | — |
Instruction Following Not comparable
Llama 3.1-405B: 65.9 (#214), Mistral Nemo: —
| Benchmark | Llama 3.1-405B | Mistral Nemo |
|---|---|---|
| IFEval | 81.1% | — |
| LMArena Instruction Following | 1259 | — |
Long Context Not comparable
Llama 3.1-405B: 38.4 (#197), Mistral Nemo: —
| Benchmark | Llama 3.1-405B | Mistral Nemo |
|---|---|---|
| LMArena Longer Query | 1266 | — |
Writing & Preference Llama 3.1-405B leads
Llama 3.1-405B: 38.9 (#251), Mistral Nemo: 28.5 (#296)
| Benchmark | Llama 3.1-405B | Mistral Nemo |
|---|---|---|
| EQ-Bench Creative Writing | 870 | 881 |
| LMArena Text | 1284 | — |
| LMArena Creative Writing | 1262 | — |
| WildBench | 78.3% | — |
| LMArena Multi-Turn | 1297 | — |
Frequently asked questions
Is Llama 3.1-405B better than Mistral Nemo?
Llama 3.1-405B is the stronger model overall, scoring 30.7 to 26.4 on the Noometry Index.
How many benchmarks do Llama 3.1-405B and Mistral Nemo share?
6 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and Mistral Nemo has 10.