Model comparison
Llama 3-8B vs Mistral Medium 3.5
Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 25.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
Meta
Mistral AISummary
- They share 17 benchmarks with published results for both. Llama 3-8B scores higher in 0 categories and Mistral Medium 3.5 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Medium 3.5 leads 40.0 to 7.8.
Side by side
| Llama 3-8B | Mistral Medium 3.5 | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 25.5 | 40.2 |
| Released | 2024-04-18 | — |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 210K |
| Input $ / M tokens | — | $1.50 |
| Output $ / M tokens | — | $7.50 |
| Results tracked | 34 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Medium 3.5 leads
Llama 3-8B: 31.0 (#289), Mistral Medium 3.5: 36.0 (#213)
| Benchmark | Llama 3-8B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Coding | 1152 | 1461 |
| LMArena WebDev | — | 1264 |
| BigCodeBench Instruct | 31.9% | — |
| BigCodeBench Complete | 36.9% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |
Reasoning Mistral Medium 3.5 leads
Llama 3-8B: 14.3 (#326), Mistral Medium 3.5: 17.3 (#295)
| Benchmark | Llama 3-8B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Hard Prompts | 1133 | 1436 |
| Epoch Capabilities Index | 116.45 | 141.35 |
| Kagi LLM Benchmark | — | 41.4% |
| NYT Connections (extended) | — | 12.9% |
| Chess Puzzles | 0% | — |
| DTBench | 43.9% | — |
| Adversarial NLI | 57.3% | — |
| ForecastBench | 58.6 | — |
| WinoGrande | 75.7% | — |
Math Mistral Medium 3.5 leads
Llama 3-8B: 8.8 (#323), Mistral Medium 3.5: 39.1 (#113)
| Benchmark | Llama 3-8B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Math | 1151 | 1431 |
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| MATH Level 5 | 6.1% | — |
Knowledge Mistral Medium 3.5 leads
Llama 3-8B: 7.8 (#308), Mistral Medium 3.5: 40.0 (#126)
| Benchmark | Llama 3-8B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Expert | 1113 | 1432 |
| GPQA Diamond | 26.1% | — |
| ARC (AI2) Challenge | 82.8% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |
Multimodal Not comparable
Llama 3-8B: —, Mistral Medium 3.5: 38.3 (#65)
| Benchmark | Llama 3-8B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Vision | — | 1223 |
Multilingual Mistral Medium 3.5 leads
Llama 3-8B: 30.8 (#261), Mistral Medium 3.5: 51.9 (#100)
| Benchmark | Llama 3-8B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Non-English | 1098 | 1404 |
| LMArena Chinese | 1076 | 1442 |
| LMArena French | 1159 | 1448 |
| LMArena German | 1104 | 1451 |
| LMArena Korean | 1004 | 1385 |
| LMArena Russian | 1109 | 1395 |
| LMArena Spanish | 1173 | 1409 |
| LMArena Japanese | 967 | — |
Instruction Following Mistral Medium 3.5 leads
Llama 3-8B: 58.4 (#260), Mistral Medium 3.5: 74.6 (#90)
| Benchmark | Llama 3-8B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Instruction Following | 1127 | 1415 |
Long Context Mistral Medium 3.5 leads
Llama 3-8B: 34.2 (#251), Mistral Medium 3.5: 43.2 (#103)
| Benchmark | Llama 3-8B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Longer Query | 1128 | 1415 |
Writing & Preference Mistral Medium 3.5 leads
Llama 3-8B: 37.5 (#256), Mistral Medium 3.5: 58.5 (#117)
| Benchmark | Llama 3-8B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Text | 1166 | 1421 |
| LMArena Creative Writing | 1150 | 1374 |
| LMArena Multi-Turn | 1152 | 1423 |
| EQ-Bench 4 | — | 993 |
Frequently asked questions
Is Llama 3-8B better than Mistral Medium 3.5?
Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 25.5 on the Noometry Index.
Is Llama 3-8B or Mistral Medium 3.5 better for coding?
Mistral Medium 3.5 scores higher on coding benchmarks: 36.0 versus 31.0 in the Noometry coding category.
How many benchmarks do Llama 3-8B and Mistral Medium 3.5 share?
17 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and Mistral Medium 3.5 has 22.