Model comparison
Llama 3-8B vs Mistral Large
Mistral Large is the stronger model overall, scoring 31.9 to 25.5 on the Noometry Index.
Last verified . 28 shared benchmarks.
Meta
Mistral AISummary
- They share 28 benchmarks with published results for both. Llama 3-8B scores higher in 0 categories and Mistral Large in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Large leads 30.1 to 7.8.
- The biggest single-benchmark swing is MATH Level 5: 6.1% for Llama 3-8B and 50.3% for Mistral Large.
Side by side
| Llama 3-8B | Mistral Large | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 25.5 | 31.9 |
| Released | 2024-04-18 | 2024-02-26 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 34 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large leads
Llama 3-8B: 31.0 (#289), Mistral Large: 34.3 (#240)
| Benchmark | Llama 3-8B | Mistral Large |
|---|---|---|
| BigCodeBench Instruct | 31.9% | 30% |
| LMArena Coding | 1152 | 1277 |
| BigCodeBench Complete | 36.9% | 38.3% |
| HumanEval+ | 56.7% | 62.2% |
| MBPP+ | 54.8% | 59.5% |
| SciCode | — | 36.2% |
| LiveBench Coding | — | 47.1% |
| ALE-Bench | — | 264.7 |
Agentic & Tool Use Not comparable
Llama 3-8B: —, Mistral Large: 28.6 (#89)
| Benchmark | Llama 3-8B | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 38.4% |
Reasoning Mistral Large leads
Llama 3-8B: 14.3 (#326), Mistral Large: 15.8 (#310)
| Benchmark | Llama 3-8B | Mistral Large |
|---|---|---|
| LMArena Hard Prompts | 1133 | 1257 |
| DTBench | 43.9% | 65.1% |
| Epoch Capabilities Index | 116.45 | 128.52 |
| ForecastBench | 58.6 | 57.1 |
| SimpleBench | — | 22.5% |
| CritPt | — | 0% |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | — | 43.5% |
| LiveBench Data Analysis | — | 50.1% |
| LMCA | — | 16.7% |
| Adversarial NLI | 57.3% | — |
| LiveBench | — | 48.4% |
| WinoGrande | 75.7% | — |
Math Mistral Large leads
Llama 3-8B: 8.8 (#323), Mistral Large: 18.2 (#291)
| Benchmark | Llama 3-8B | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | 8.5% |
| LMArena Math | 1151 | 1262 |
| MATH Level 5 | 6.1% | 50.3% |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Mistral Large leads
Llama 3-8B: 7.8 (#308), Mistral Large: 30.1 (#230)
| Benchmark | Llama 3-8B | Mistral Large |
|---|---|---|
| GPQA Diamond | 26.1% | 51.3% |
| LMArena Expert | 1113 | 1232 |
| MMLU | 68.8% | 80% |
| MMLU-Pro | — | 59.9% |
| Confabulations | — | 21.4% |
| Vectara Hallucination Rate | — | 4.5% |
| GPQA (HELM) | — | 43.5% |
| ARC (AI2) Challenge | 82.8% | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |
Multilingual Mistral Large leads
Llama 3-8B: 30.8 (#261), Mistral Large: 40.0 (#219)
| Benchmark | Llama 3-8B | Mistral Large |
|---|---|---|
| LMArena Non-English | 1098 | 1237 |
| LMArena Chinese | 1076 | 1240 |
| LMArena French | 1159 | 1325 |
| LMArena German | 1104 | 1254 |
| LMArena Japanese | 967 | 1188 |
| LMArena Korean | 1004 | 1202 |
| LMArena Russian | 1109 | 1257 |
| LMArena Spanish | 1173 | 1268 |
Instruction Following Mistral Large leads
Llama 3-8B: 58.4 (#260), Mistral Large: 67.9 (#191)
| Benchmark | Llama 3-8B | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1127 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |
Long Context Mistral Large leads
Llama 3-8B: 34.2 (#251), Mistral Large: 38.3 (#199)
| Benchmark | Llama 3-8B | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1128 | 1261 |
Writing & Preference Mistral Large leads
Llama 3-8B: 37.5 (#256), Mistral Large: 40.7 (#242)
| Benchmark | Llama 3-8B | Mistral Large |
|---|---|---|
| LMArena Text | 1166 | 1266 |
| LMArena Creative Writing | 1150 | 1243 |
| LMArena Multi-Turn | 1152 | 1260 |
| Short-Story Creative Writing | — | 69% |
| EQ-Bench Creative Writing | — | 985 |
| WildBench | — | 80.1% |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is Llama 3-8B better than Mistral Large?
Mistral Large is the stronger model overall, scoring 31.9 to 25.5 on the Noometry Index.
Is Llama 3-8B or Mistral Large better for coding?
Mistral Large scores higher on coding benchmarks: 34.3 versus 31.0 in the Noometry coding category.
How many benchmarks do Llama 3-8B and Mistral Large share?
28 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and Mistral Large has 51.