Model comparison
Llama 3-70B vs Mistral Small 3.2
Mistral Small 3.2 is the stronger model overall, scoring 31.2 to 28.8 on the Noometry Index.
Last verified . 4 shared benchmarks.
Meta
Mistral AISummary
- They share 4 benchmarks with published results for both. Llama 3-70B scores higher in 0 categories and Mistral Small 3.2 in 4 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral Small 3.2 leads 26.3 to 12.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.3% for Llama 3-70B and 30.3% for Mistral Small 3.2.
Side by side
| Llama 3-70B | Mistral Small 3.2 | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 28.8 | 31.2 |
| Released | 2024-04-18 | 2025-06-20 |
| Weights | Open | Open |
| Context window | — | 256K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.0938 |
| Output $ / M tokens | — | $0.25 |
| Results tracked | 31 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3-70B: 35.8 (#218), Mistral Small 3.2: —
| Benchmark | Llama 3-70B | Mistral Small 3.2 |
|---|---|---|
| BigCodeBench Instruct | 43.6% | — |
| LMArena Coding | 1206 | — |
| BigCodeBench Complete | 54.5% | — |
| HumanEval+ | 72% | — |
| MBPP+ | 69% | — |
Agentic & Tool Use Not comparable
Llama 3-70B: 21.1 (#139), Mistral Small 3.2: —
| Benchmark | Llama 3-70B | Mistral Small 3.2 |
|---|---|---|
| Cybench | 5% | — |
Reasoning Too close to call
Llama 3-70B: 18.0 (#288), Mistral Small 3.2: 18.1 (#287)
| Benchmark | Llama 3-70B | Mistral Small 3.2 |
|---|---|---|
| Kagi LLM Benchmark | 35.1% | 40.4% |
| Epoch Capabilities Index | 122.93 | 131.74 |
| Chess Puzzles | — | 1% |
| LMArena Hard Prompts | 1195 | — |
| DTBench | 54.2% | — |
| ForecastBench | 57.1 | — |
| WinoGrande | 83.5% | — |
Math Mistral Small 3.2 leads
Llama 3-70B: 12.8 (#305), Mistral Small 3.2: 26.3 (#260)
| Benchmark | Llama 3-70B | Mistral Small 3.2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | 30.3% |
| LMArena Math | 1218 | — |
| MATH Level 5 | 22.6% | — |
Knowledge Mistral Small 3.2 leads
Llama 3-70B: 20.8 (#277), Mistral Small 3.2: 26.7 (#256)
| Benchmark | Llama 3-70B | Mistral Small 3.2 |
|---|---|---|
| GPQA Diamond | 40.6% | 49.1% |
| LMArena Expert | 1149 | — |
| MMLU | 79.3% | — |
Multilingual Not comparable
Llama 3-70B: 33.6 (#251), Mistral Small 3.2: —
| Benchmark | Llama 3-70B | Mistral Small 3.2 |
|---|---|---|
| LMArena Non-English | 1142 | — |
| LMArena Chinese | 1114 | — |
| LMArena French | 1232 | — |
| LMArena German | 1169 | — |
| LMArena Japanese | 1017 | — |
| LMArena Korean | 1017 | — |
| LMArena Russian | 1159 | — |
| LMArena Spanish | 1241 | — |
Instruction Following Not comparable
Llama 3-70B: 62.5 (#238), Mistral Small 3.2: —
| Benchmark | Llama 3-70B | Mistral Small 3.2 |
|---|---|---|
| LMArena Instruction Following | 1194 | — |
Long Context Not comparable
Llama 3-70B: 35.6 (#240), Mistral Small 3.2: —
| Benchmark | Llama 3-70B | Mistral Small 3.2 |
|---|---|---|
| LMArena Longer Query | 1174 | — |
Writing & Preference Mistral Small 3.2 leads
Llama 3-70B: 42.8 (#231), Mistral Small 3.2: 45.0 (#224)
| Benchmark | Llama 3-70B | Mistral Small 3.2 |
|---|---|---|
| LMArena Text | 1221 | — |
| LMArena Creative Writing | 1210 | — |
| EQ-Bench Creative Writing | — | 1255 |
| LMArena Multi-Turn | 1223 | — |
Frequently asked questions
Is Llama 3-70B better than Mistral Small 3.2?
Mistral Small 3.2 is the stronger model overall, scoring 31.2 to 28.8 on the Noometry Index.
How many benchmarks do Llama 3-70B and Mistral Small 3.2 share?
4 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and Mistral Small 3.2 has 6.