Model comparison
Llama 3-70B vs Mistral Small 3
Mistral Small 3 is the stronger model overall, scoring 30.9 to 28.5 on the Noometry Index.
Last verified . 21 shared benchmarks.
Meta
Mistral AISummary
- They share 21 benchmarks with published results for both. Llama 3-70B scores higher in 1 category and Mistral Small 3 in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Llama 3-70B leads 43.0 to 32.4.
- The biggest single-benchmark swing is GPQA Diamond: 40.6% for Llama 3-70B and 47.3% for Mistral Small 3.
Side by side
| Llama 3-70B | Mistral Small 3 | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 28.5 | 30.9 |
| Released | 2024-04-18 | 2025-01-30 |
| Weights | Open | Open |
| Context window | — | 33K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.05 |
| Output $ / M tokens | — | $0.08 |
| Results tracked | 31 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Llama 3-70B: 35.3 (#215), Mistral Small 3: 36.0 (#203)
| Benchmark | Llama 3-70B | Mistral Small 3 |
|---|---|---|
| BigCodeBench Instruct | 43.6% | 45.3% |
| LMArena Coding | 1206 | 1246 |
| BigCodeBench Complete | 54.5% | 50.4% |
| HumanEval+ | 72% | — |
| MBPP+ | 69% | — |
Agentic & Tool Use Not comparable
Llama 3-70B: 20.9 (#132), Mistral Small 3: —
| Benchmark | Llama 3-70B | Mistral Small 3 |
|---|---|---|
| Cybench | 5% | — |
Reasoning Too close to call
Llama 3-70B: 17.4 (#284), Mistral Small 3: 18.2 (#269)
| Benchmark | Llama 3-70B | Mistral Small 3 |
|---|---|---|
| LMArena Hard Prompts | 1195 | 1233 |
| Epoch Capabilities Index | 122.91 | 127.06 |
| Kagi LLM Benchmark | 35.1% | — |
| Chess Puzzles | — | 0% |
| DTBench | 54.2% | — |
| ForecastBench | 57.1 | — |
| WinoGrande | 83.5% | — |
Math Mistral Small 3 leads
Llama 3-70B: 12.0 (#299), Mistral Small 3: 15.3 (#290)
| Benchmark | Llama 3-70B | Mistral Small 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | 6.7% |
| LMArena Math | 1218 | 1240 |
| MATH Level 5 | 22.6% | — |
Knowledge Mistral Small 3 leads
Llama 3-70B: 20.8 (#272), Mistral Small 3: 25.0 (#258)
| Benchmark | Llama 3-70B | Mistral Small 3 |
|---|---|---|
| GPQA Diamond | 40.6% | 47.3% |
| LMArena Expert | 1149 | 1202 |
| Confabulations | — | 25.2% |
| MMLU | 79.3% | — |
Multilingual Mistral Small 3 leads
Llama 3-70B: 33.8 (#246), Mistral Small 3: 37.5 (#231)
| Benchmark | Llama 3-70B | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1142 | 1198 |
| LMArena Chinese | 1114 | 1204 |
| LMArena French | 1231 | 1202 |
| LMArena German | 1169 | 1211 |
| LMArena Japanese | 1017 | 1111 |
| LMArena Korean | 1017 | 1188 |
| LMArena Russian | 1159 | 1216 |
| LMArena Spanish | 1241 | — |
Instruction Following Mistral Small 3 leads
Llama 3-70B: 62.8 (#233), Mistral Small 3: 63.9 (#224)
| Benchmark | Llama 3-70B | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1194 | 1214 |
Long Context Mistral Small 3 leads
Llama 3-70B: 35.6 (#235), Mistral Small 3: 37.8 (#206)
| Benchmark | Llama 3-70B | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1174 | 1246 |
Writing & Preference Llama 3-70B leads
Llama 3-70B: 43.0 (#225), Mistral Small 3: 32.4 (#275)
| Benchmark | Llama 3-70B | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1221 | 1234 |
| LMArena Creative Writing | 1210 | 1195 |
| LMArena Multi-Turn | 1223 | 1217 |
| EQ-Bench Creative Writing | — | 707 |
Frequently asked questions
Is Llama 3-70B better than Mistral Small 3?
Mistral Small 3 is the stronger model overall, scoring 30.9 to 28.5 on the Noometry Index.
Is Llama 3-70B or Mistral Small 3 better for coding?
They score almost the same on coding (35.3 vs 36.0); test both on your own repository before choosing.
How many benchmarks do Llama 3-70B and Mistral Small 3 share?
21 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and Mistral Small 3 has 24.