Model comparison
Llama 3-8B vs Mistral Small 3.1
Mistral Small 3.1 is the stronger model overall, scoring 31.7 to 25.5 on the Noometry Index.
Last verified . 21 shared benchmarks.
Meta
Mistral AISummary
- They share 21 benchmarks with published results for both. Llama 3-8B scores higher in 1 category and Mistral Small 3.1 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Small 3.1 leads 22.6 to 7.8.
- The biggest single-benchmark swing is GPQA Diamond: 26.1% for Llama 3-8B and 41.9% for Mistral Small 3.1.
Side by side
| Llama 3-8B | Mistral Small 3.1 | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 25.5 | 31.7 |
| Released | 2024-04-18 | 2025-03-17 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 102K |
| Input $ / M tokens | — | $0.35 |
| Output $ / M tokens | — | $0.56 |
| Results tracked | 34 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3.1 leads
Llama 3-8B: 31.0 (#289), Mistral Small 3.1: 38.3 (#179)
| Benchmark | Llama 3-8B | Mistral Small 3.1 |
|---|---|---|
| LMArena Coding | 1152 | 1309 |
| BigCodeBench Instruct | 31.9% | — |
| BigCodeBench Complete | 36.9% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |
Reasoning Mistral Small 3.1 leads
Llama 3-8B: 14.3 (#326), Mistral Small 3.1: 19.7 (#254)
| Benchmark | Llama 3-8B | Mistral Small 3.1 |
|---|---|---|
| Chess Puzzles | 0% | 1% |
| LMArena Hard Prompts | 1133 | 1278 |
| Epoch Capabilities Index | 116.45 | 127.48 |
| DTBench | 43.9% | — |
| Adversarial NLI | 57.3% | — |
| ForecastBench | 58.6 | — |
| WinoGrande | 75.7% | — |
Math Mistral Small 3.1 leads
Llama 3-8B: 8.8 (#323), Mistral Small 3.1: 14.7 (#301)
| Benchmark | Llama 3-8B | Mistral Small 3.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | 3.9% |
| LMArena Math | 1151 | 1262 |
| Omni-MATH | — | 24.8% |
| MATH Level 5 | 6.1% | — |
Knowledge Mistral Small 3.1 leads
Llama 3-8B: 7.8 (#308), Mistral Small 3.1: 22.6 (#271)
| Benchmark | Llama 3-8B | Mistral Small 3.1 |
|---|---|---|
| GPQA Diamond | 26.1% | 41.9% |
| LMArena Expert | 1113 | 1257 |
| MMLU-Pro | — | 61% |
| GPQA (HELM) | — | 39.2% |
| ARC (AI2) Challenge | 82.8% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |
Multimodal Not comparable
Llama 3-8B: —, Mistral Small 3.1: 33.2 (#99)
| Benchmark | Llama 3-8B | Mistral Small 3.1 |
|---|---|---|
| LMArena Vision | — | 1136 |
Multilingual Mistral Small 3.1 leads
Llama 3-8B: 30.8 (#261), Mistral Small 3.1: 41.2 (#209)
| Benchmark | Llama 3-8B | Mistral Small 3.1 |
|---|---|---|
| LMArena Non-English | 1098 | 1255 |
| LMArena Chinese | 1076 | 1253 |
| LMArena French | 1159 | 1273 |
| LMArena German | 1104 | 1266 |
| LMArena Japanese | 967 | 1208 |
| LMArena Korean | 1004 | 1206 |
| LMArena Russian | 1109 | 1263 |
| LMArena Spanish | 1173 | 1283 |
Instruction Following Mistral Small 3.1 leads
Llama 3-8B: 58.4 (#260), Mistral Small 3.1: 63.6 (#230)
| Benchmark | Llama 3-8B | Mistral Small 3.1 |
|---|---|---|
| LMArena Instruction Following | 1127 | 1264 |
| IFEval | — | 75% |
Long Context Mistral Small 3.1 leads
Llama 3-8B: 34.2 (#251), Mistral Small 3.1: 39.5 (#178)
| Benchmark | Llama 3-8B | Mistral Small 3.1 |
|---|---|---|
| LMArena Longer Query | 1128 | 1299 |
Writing & Preference Too close to call
Llama 3-8B: 37.5 (#256), Mistral Small 3.1: 37.0 (#259)
| Benchmark | Llama 3-8B | Mistral Small 3.1 |
|---|---|---|
| LMArena Text | 1166 | 1277 |
| LMArena Creative Writing | 1150 | 1253 |
| LMArena Multi-Turn | 1152 | 1270 |
| EQ-Bench Creative Writing | — | 761 |
| WildBench | — | 78.8% |
Frequently asked questions
Is Llama 3-8B better than Mistral Small 3.1?
Mistral Small 3.1 is the stronger model overall, scoring 31.7 to 25.5 on the Noometry Index.
Is Llama 3-8B or Mistral Small 3.1 better for coding?
Mistral Small 3.1 scores higher on coding benchmarks: 38.3 versus 31.0 in the Noometry coding category.
How many benchmarks do Llama 3-8B and Mistral Small 3.1 share?
21 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and Mistral Small 3.1 has 28.