Model comparison
Llama 3.1-8B vs Mistral
Mistral is the stronger model overall, scoring 29.9 to 23.0 on the Noometry Index.
Last verified . 22 shared benchmarks.
Meta
Mistral AISummary
- They share 22 benchmarks with published results for both. Llama 3.1-8B scores higher in 3 categories and Mistral in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Mistral leads 33.8 to 20.2.
- The biggest single-benchmark swing is IFEval: 74.3% for Llama 3.1-8B and 56.8% for Mistral.
- Llama 3.1-8B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.1-8B | Mistral | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 23.0 | 29.9 |
| Released | 2024-07-23 | — |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 43 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral leads
Llama 3.1-8B: 20.2 (#340), Mistral: 33.8 (#250)
| Benchmark | Llama 3.1-8B | Mistral |
|---|---|---|
| LMArena Coding | 1195 | 1162 |
| SciCode | 13.2% | — |
| WeirdML | 1.7% | — |
| BigCodeBench Instruct | 32.8% | — |
| BigCodeBench Complete | 40.5% | — |
| HumanEval+ | 62.8% | — |
| MBPP+ | 55.6% | — |
Agentic & Tool Use Not comparable
Llama 3.1-8B: 22.5 (#131), Mistral: —
| Benchmark | Llama 3.1-8B | Mistral |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25.8% | — |
| BALROG | 15.1% | — |
Reasoning Mistral leads
Llama 3.1-8B: 14.9 (#321), Mistral: 22.2 (#200)
| Benchmark | Llama 3.1-8B | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1175 | 1149 |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| DTBench | 50.9% | — |
| LMCA | 5.4% | — |
| Epoch Capabilities Index | 116.57 | — |
| PIQA | 81.2% | — |
Math Mistral leads
Llama 3.1-8B: 10.2 (#317), Mistral: 22.3 (#278)
| Benchmark | Llama 3.1-8B | Mistral |
|---|---|---|
| Omni-MATH | 13.7% | 7.2% |
| LMArena Math | 1179 | 1180 |
| OTIS Mock AIME 2024-2025 | 1.7% | — |
| MATH Level 5 | 22.9% | — |
| GSM8K | 82.4% | — |
Knowledge Mistral leads
Llama 3.1-8B: 8.0 (#307), Mistral: 16.6 (#288)
| Benchmark | Llama 3.1-8B | Mistral |
|---|---|---|
| MMLU-Pro | 40.6% | 27.7% |
| GPQA (HELM) | 24.7% | 30.3% |
| LMArena Expert | 1144 | 1125 |
| GPQA Diamond | 27% | — |
| BoolQ | 82.8% | — |
| MMLU | 56.1% | — |
Multilingual Llama 3.1-8B leads
Llama 3.1-8B: 34.0 (#249), Mistral: 32.8 (#254)
| Benchmark | Llama 3.1-8B | Mistral |
|---|---|---|
| LMArena Non-English | 1148 | 1129 |
| LMArena Chinese | 1151 | 1109 |
| LMArena French | 1177 | 1180 |
| LMArena German | 1144 | 1155 |
| LMArena Japanese | 1061 | 1013 |
| LMArena Korean | 1053 | 1032 |
| LMArena Russian | 1158 | 1168 |
| LMArena Spanish | 1169 | 1143 |
Instruction Following Llama 3.1-8B leads
Llama 3.1-8B: 58.9 (#258), Mistral: 52.6 (#288)
| Benchmark | Llama 3.1-8B | Mistral |
|---|---|---|
| IFEval | 74.3% | 56.8% |
| LMArena Instruction Following | 1159 | 1152 |
Long Context Too close to call
Llama 3.1-8B: 35.8 (#238), Mistral: 35.0 (#245)
| Benchmark | Llama 3.1-8B | Mistral |
|---|---|---|
| LMArena Longer Query | 1182 | 1153 |
Writing & Preference Mistral leads
Llama 3.1-8B: 29.7 (#290), Mistral: 37.0 (#260)
| Benchmark | Llama 3.1-8B | Mistral |
|---|---|---|
| LMArena Text | 1187 | 1165 |
| LMArena Creative Writing | 1154 | 1158 |
| WildBench | 68.7% | 66% |
| LMArena Multi-Turn | 1172 | 1147 |
| EQ-Bench Creative Writing | 713 | — |
Frequently asked questions
Is Llama 3.1-8B better than Mistral?
Mistral is the stronger model overall, scoring 29.9 to 23.0 on the Noometry Index.
Is Llama 3.1-8B or Mistral better for coding?
Mistral scores higher on coding benchmarks: 33.8 versus 20.2 in the Noometry coding category.
How many benchmarks do Llama 3.1-8B and Mistral share?
22 benchmarks have published results for both models. Llama 3.1-8B has 43 scored results on Noometry and Mistral has 22.