Model comparison
Llama 3-70B vs Mistral
Mistral is the stronger model overall, scoring 29.9 to 28.8 on the Noometry Index.
Last verified . 17 shared benchmarks.
Meta
Mistral AISummary
- They share 17 benchmarks with published results for both. Llama 3-70B scores higher in 6 categories and Mistral in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Llama 3-70B leads 62.5 to 52.6.
- Llama 3-70B has downloadable open weights; the other is API-only.
Side by side
| Llama 3-70B | Mistral | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 28.8 | 29.9 |
| Released | 2024-04-18 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 31 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-70B leads
Llama 3-70B: 35.8 (#218), Mistral: 33.8 (#250)
| Benchmark | Llama 3-70B | Mistral |
|---|---|---|
| LMArena Coding | 1206 | 1162 |
| BigCodeBench Instruct | 43.6% | — |
| BigCodeBench Complete | 54.5% | — |
| HumanEval+ | 72% | — |
| MBPP+ | 69% | — |
Agentic & Tool Use Not comparable
Llama 3-70B: 21.1 (#139), Mistral: —
| Benchmark | Llama 3-70B | Mistral |
|---|---|---|
| Cybench | 5% | — |
Reasoning Mistral leads
Llama 3-70B: 18.0 (#288), Mistral: 22.2 (#200)
| Benchmark | Llama 3-70B | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1195 | 1149 |
| Kagi LLM Benchmark | 35.1% | — |
| DTBench | 54.2% | — |
| Epoch Capabilities Index | 122.93 | — |
| ForecastBench | 57.1 | — |
| WinoGrande | 83.5% | — |
Math Mistral leads
Llama 3-70B: 12.8 (#305), Mistral: 22.3 (#278)
| Benchmark | Llama 3-70B | Mistral |
|---|---|---|
| LMArena Math | 1218 | 1180 |
| OTIS Mock AIME 2024-2025 | 4.3% | — |
| Omni-MATH | — | 7.2% |
| MATH Level 5 | 22.6% | — |
Knowledge Llama 3-70B leads
Llama 3-70B: 20.8 (#277), Mistral: 16.6 (#288)
| Benchmark | Llama 3-70B | Mistral |
|---|---|---|
| LMArena Expert | 1149 | 1125 |
| GPQA Diamond | 40.6% | — |
| MMLU-Pro | — | 27.7% |
| GPQA (HELM) | — | 30.3% |
| MMLU | 79.3% | — |
Multilingual Too close to call
Llama 3-70B: 33.6 (#251), Mistral: 32.8 (#254)
| Benchmark | Llama 3-70B | Mistral |
|---|---|---|
| LMArena Non-English | 1142 | 1129 |
| LMArena Chinese | 1114 | 1109 |
| LMArena French | 1232 | 1180 |
| LMArena German | 1169 | 1155 |
| LMArena Japanese | 1017 | 1013 |
| LMArena Korean | 1017 | 1032 |
| LMArena Russian | 1159 | 1168 |
| LMArena Spanish | 1241 | 1143 |
Instruction Following Llama 3-70B leads
Llama 3-70B: 62.5 (#238), Mistral: 52.6 (#288)
| Benchmark | Llama 3-70B | Mistral |
|---|---|---|
| LMArena Instruction Following | 1194 | 1152 |
| IFEval | — | 56.8% |
Long Context Too close to call
Llama 3-70B: 35.6 (#240), Mistral: 35.0 (#245)
| Benchmark | Llama 3-70B | Mistral |
|---|---|---|
| LMArena Longer Query | 1174 | 1153 |
Writing & Preference Llama 3-70B leads
Llama 3-70B: 42.8 (#231), Mistral: 37.0 (#260)
| Benchmark | Llama 3-70B | Mistral |
|---|---|---|
| LMArena Text | 1221 | 1165 |
| LMArena Creative Writing | 1210 | 1158 |
| LMArena Multi-Turn | 1223 | 1147 |
| WildBench | — | 66% |
Frequently asked questions
Is Llama 3-70B better than Mistral?
Mistral is the stronger model overall, scoring 29.9 to 28.8 on the Noometry Index.
Is Llama 3-70B or Mistral better for coding?
Llama 3-70B scores higher on coding benchmarks: 35.8 versus 33.8 in the Noometry coding category.
How many benchmarks do Llama 3-70B and Mistral share?
17 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and Mistral has 22.