Model comparison
Llama 3-8B vs Mistral Small
Mistral Small is the stronger model overall, scoring 33.4 to 25.5 on the Noometry Index.
Last verified . 24 shared benchmarks.
Meta
Mistral AISummary
- They share 24 benchmarks with published results for both. Llama 3-8B scores higher in 0 categories and Mistral Small in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Small leads 31.0 to 7.8.
- The biggest single-benchmark swing is MATH Level 5: 6.1% for Llama 3-8B and 46.8% for Mistral Small.
Side by side
| Llama 3-8B | Mistral Small | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 25.5 | 33.4 |
| Released | 2024-04-18 | 2024-02-26 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 256K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.60 |
| Results tracked | 34 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small leads
Llama 3-8B: 31.0 (#289), Mistral Small: 34.0 (#247)
| Benchmark | Llama 3-8B | Mistral Small |
|---|---|---|
| BigCodeBench Instruct | 31.9% | 36.1% |
| LMArena Coding | 1152 | 1362 |
| BigCodeBench Complete | 36.9% | 46.6% |
| SciCode | — | 26.5% |
| LiveBench Coding | — | 36.2% |
| ALE-Bench | — | 497.62 |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |
Agentic & Tool Use Not comparable
Llama 3-8B: —, Mistral Small: 28.1 (#93)
| Benchmark | Llama 3-8B | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |
Reasoning Mistral Small leads
Llama 3-8B: 14.3 (#326), Mistral Small: 19.8 (#250)
| Benchmark | Llama 3-8B | Mistral Small |
|---|---|---|
| LMArena Hard Prompts | 1133 | 1335 |
| DTBench | 43.9% | 70.9% |
| Kagi LLM Benchmark | — | 37.8% |
| CritPt | — | 0% |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | — | 44.8% |
| LiveBench Data Analysis | — | 53.7% |
| LMCA | — | 20.6% |
| Adversarial NLI | 57.3% | — |
| Epoch Capabilities Index | 116.45 | — |
| ForecastBench | 58.6 | — |
| LiveBench | — | 44% |
| WinoGrande | 75.7% | — |
Math Mistral Small leads
Llama 3-8B: 8.8 (#323), Mistral Small: 16.4 (#293)
| Benchmark | Llama 3-8B | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | 5.8% |
| LMArena Math | 1151 | 1341 |
| MATH Level 5 | 6.1% | 46.8% |
| LiveBench Math | — | 39.9% |
Knowledge Mistral Small leads
Llama 3-8B: 7.8 (#308), Mistral Small: 31.0 (#222)
| Benchmark | Llama 3-8B | Mistral Small |
|---|---|---|
| GPQA Diamond | 26.1% | 47.5% |
| LMArena Expert | 1113 | 1291 |
| MMLU | 68.8% | 68.7% |
| Vectara Hallucination Rate | — | 5.1% |
| ARC (AI2) Challenge | 82.8% | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |
Multimodal Not comparable
Llama 3-8B: —, Mistral Small: 33.5 (#96)
| Benchmark | Llama 3-8B | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |
Multilingual Mistral Small leads
Llama 3-8B: 30.8 (#261), Mistral Small: 45.5 (#169)
| Benchmark | Llama 3-8B | Mistral Small |
|---|---|---|
| LMArena Non-English | 1098 | 1315 |
| LMArena Chinese | 1076 | 1340 |
| LMArena French | 1159 | 1337 |
| LMArena German | 1104 | 1340 |
| LMArena Japanese | 967 | 1275 |
| LMArena Korean | 1004 | 1259 |
| LMArena Russian | 1109 | 1324 |
| LMArena Spanish | 1173 | 1346 |
Instruction Following Mistral Small leads
Llama 3-8B: 58.4 (#260), Mistral Small: 66.4 (#209)
| Benchmark | Llama 3-8B | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1127 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
Long Context Mistral Small leads
Llama 3-8B: 34.2 (#251), Mistral Small: 40.4 (#156)
| Benchmark | Llama 3-8B | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1128 | 1327 |
Writing & Preference Mistral Small leads
Llama 3-8B: 37.5 (#256), Mistral Small: 52.5 (#171)
| Benchmark | Llama 3-8B | Mistral Small |
|---|---|---|
| LMArena Text | 1166 | 1338 |
| LMArena Creative Writing | 1150 | 1305 |
| LMArena Multi-Turn | 1152 | 1344 |
| LiveBench Language | — | 30.5% |
Frequently asked questions
Is Llama 3-8B better than Mistral Small?
Mistral Small is the stronger model overall, scoring 33.4 to 25.5 on the Noometry Index.
Is Llama 3-8B or Mistral Small better for coding?
Mistral Small scores higher on coding benchmarks: 34.0 versus 31.0 in the Noometry coding category.
How many benchmarks do Llama 3-8B and Mistral Small share?
24 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and Mistral Small has 39.