Model comparison
Llama 3.1-70B vs Mistral
Llama 3.1-70B and Mistral score almost the same on the Noometry Index (29.6 vs 29.9), so choose on price, context window or the category you care about most.
Last verified . 22 shared benchmarks.
Meta
Mistral AISummary
- They share 22 benchmarks with published results for both. Llama 3.1-70B scores higher in 4 categories and Mistral in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Llama 3.1-70B leads 65.3 to 52.6.
- The biggest single-benchmark swing is MMLU-Pro: 65.3% for Llama 3.1-70B and 27.7% for Mistral.
- Llama 3.1-70B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.1-70B | Mistral | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 29.6 | 29.9 |
| Released | 2024-07-23 | — |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.40 | — |
| Output $ / M tokens | $0.40 | — |
| Results tracked | 35 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral leads
Llama 3.1-70B: 30.3 (#296), Mistral: 33.8 (#250)
| Benchmark | Llama 3.1-70B | Mistral |
|---|---|---|
| LMArena Coding | 1260 | 1162 |
| WeirdML | 9% | — |
| BigCodeBench Instruct | 46.1% | — |
| BigCodeBench Complete | 54.8% | — |
Agentic & Tool Use Not comparable
Llama 3.1-70B: 25.1 (#112), Mistral: —
| Benchmark | Llama 3.1-70B | Mistral |
|---|---|---|
| TheAgentCompany | 6.9% | — |
| BALROG | 27.9% | — |
Reasoning Too close to call
Llama 3.1-70B: 21.6 (#220), Mistral: 22.2 (#200)
| Benchmark | Llama 3.1-70B | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1149 |
| DTBench | 60% | — |
| LMCA | 14.8% | — |
| Epoch Capabilities Index | 125.92 | — |
Math Mistral leads
Llama 3.1-70B: 13.5 (#304), Mistral: 22.3 (#278)
| Benchmark | Llama 3.1-70B | Mistral |
|---|---|---|
| Omni-MATH | 21% | 7.2% |
| LMArena Math | 1252 | 1180 |
| OTIS Mock AIME 2024-2025 | 3.6% | — |
| MATH Level 5 | 36.7% | — |
Knowledge Llama 3.1-70B leads
Llama 3.1-70B: 24.2 (#269), Mistral: 16.6 (#288)
| Benchmark | Llama 3.1-70B | Mistral |
|---|---|---|
| MMLU-Pro | 65.3% | 27.7% |
| GPQA (HELM) | 42.6% | 30.3% |
| LMArena Expert | 1209 | 1125 |
| GPQA Diamond | 44.2% | — |
| MMLU | 80.1% | — |
Multilingual Llama 3.1-70B leads
Llama 3.1-70B: 38.8 (#225), Mistral: 32.8 (#254)
| Benchmark | Llama 3.1-70B | Mistral |
|---|---|---|
| LMArena Non-English | 1219 | 1129 |
| LMArena Chinese | 1215 | 1109 |
| LMArena French | 1261 | 1180 |
| LMArena German | 1222 | 1155 |
| LMArena Japanese | 1132 | 1013 |
| LMArena Korean | 1140 | 1032 |
| LMArena Russian | 1234 | 1168 |
| LMArena Spanish | 1253 | 1143 |
Instruction Following Llama 3.1-70B leads
Llama 3.1-70B: 65.3 (#223), Mistral: 52.6 (#288)
| Benchmark | Llama 3.1-70B | Mistral |
|---|---|---|
| IFEval | 82.1% | 56.8% |
| LMArena Instruction Following | 1231 | 1152 |
Long Context Llama 3.1-70B leads
Llama 3.1-70B: 37.6 (#214), Mistral: 35.0 (#245)
| Benchmark | Llama 3.1-70B | Mistral |
|---|---|---|
| LMArena Longer Query | 1241 | 1153 |
Writing & Preference Mistral leads
Llama 3.1-70B: 35.4 (#267), Mistral: 37.0 (#260)
| Benchmark | Llama 3.1-70B | Mistral |
|---|---|---|
| LMArena Text | 1261 | 1165 |
| LMArena Creative Writing | 1232 | 1158 |
| WildBench | 75.8% | 66% |
| LMArena Multi-Turn | 1256 | 1147 |
| EQ-Bench Creative Writing | 784 | — |
Frequently asked questions
Is Llama 3.1-70B better than Mistral?
Llama 3.1-70B and Mistral score almost the same on the Noometry Index (29.6 vs 29.9), so choose on price, context window or the category you care about most.
Is Llama 3.1-70B or Mistral better for coding?
Mistral scores higher on coding benchmarks: 33.8 versus 30.3 in the Noometry coding category.
How many benchmarks do Llama 3.1-70B and Mistral share?
22 benchmarks have published results for both models. Llama 3.1-70B has 35 scored results on Noometry and Mistral has 22.