Model comparison
Llama 2-70B vs Mistral Small 3
Mistral Small 3 is the stronger model overall, scoring 31.2 to 24.4 on the Noometry Index.
Last verified . 19 shared benchmarks.
Meta
Mistral AISummary
- They share 19 benchmarks with published results for both. Llama 2-70B scores higher in 1 category and Mistral Small 3 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Small 3 leads 25.1 to 7.4.
- The biggest single-benchmark swing is GPQA Diamond: 26.3% for Llama 2-70B and 47.3% for Mistral Small 3.
Side by side
| Llama 2-70B | Mistral Small 3 | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 24.4 | 31.2 |
| Released | 2023-07-18 | 2025-01-30 |
| Weights | Open | Open |
| Context window | — | 33K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.05 |
| Output $ / M tokens | — | $0.08 |
| Results tracked | 35 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3 leads
Llama 2-70B: 31.4 (#286), Mistral Small 3: 36.5 (#207)
| Benchmark | Llama 2-70B | Mistral Small 3 |
|---|---|---|
| LMArena Coding | 1079 | 1246 |
| BigCodeBench Instruct | — | 45.3% |
| BigCodeBench Complete | — | 50.4% |
Reasoning Mistral Small 3 leads
Llama 2-70B: 14.4 (#325), Mistral Small 3: 18.9 (#273)
| Benchmark | Llama 2-70B | Mistral Small 3 |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1233 |
| Epoch Capabilities Index | 113.79 | 127.07 |
| Chess Puzzles | — | 0% |
| DTBench | 41.6% | — |
| BIG-Bench Hard | 64.9% | — |
| CommonsenseQA 2.0 | 50% | — |
| ForecastBench | 51.4 | — |
| HellaSwag | 85.3% | — |
| LAMBADA | 78.9% | — |
| PIQA | 82.8% | — |
| WinoGrande | 80.2% | — |
Math Mistral Small 3 leads
Llama 2-70B: 8.1 (#326), Mistral Small 3: 16.3 (#295)
| Benchmark | Llama 2-70B | Mistral Small 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0% | 6.7% |
| LMArena Math | 1091 | 1240 |
| MATH Level 5 | 3.3% | — |
| GSM8K | 69.6% | — |
Knowledge Mistral Small 3 leads
Llama 2-70B: 7.4 (#310), Mistral Small 3: 25.1 (#263)
| Benchmark | Llama 2-70B | Mistral Small 3 |
|---|---|---|
| GPQA Diamond | 26.3% | 47.3% |
| LMArena Expert | 1039 | 1202 |
| Confabulations | — | 25.2% |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 88.6% | — |
| MMLU | 69.9% | — |
| OpenBookQA | 60.2% | — |
| TriviaQA | 87.6% | — |
Multilingual Mistral Small 3 leads
Llama 2-70B: 27.7 (#274), Mistral Small 3: 37.3 (#236)
| Benchmark | Llama 2-70B | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1045 | 1198 |
| LMArena Chinese | 995 | 1204 |
| LMArena French | 1090 | 1203 |
| LMArena German | 1041 | 1211 |
| LMArena Japanese | 927 | 1111 |
| LMArena Korean | 964 | 1188 |
| LMArena Russian | 1083 | 1216 |
| LMArena Spanish | 1143 | — |
Instruction Following Mistral Small 3 leads
Llama 2-70B: 54.9 (#278), Mistral Small 3: 63.7 (#229)
| Benchmark | Llama 2-70B | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1071 | 1214 |
Long Context Mistral Small 3 leads
Llama 2-70B: 32.3 (#270), Mistral Small 3: 37.8 (#211)
| Benchmark | Llama 2-70B | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1062 | 1246 |
Writing & Preference Too close to call
Llama 2-70B: 32.3 (#279), Mistral Small 3: 32.2 (#280)
| Benchmark | Llama 2-70B | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1115 | 1234 |
| LMArena Creative Writing | 1075 | 1195 |
| LMArena Multi-Turn | 1088 | 1217 |
| EQ-Bench Creative Writing | — | 707 |
Frequently asked questions
Is Llama 2-70B better than Mistral Small 3?
Mistral Small 3 is the stronger model overall, scoring 31.2 to 24.4 on the Noometry Index.
Is Llama 2-70B or Mistral Small 3 better for coding?
Mistral Small 3 scores higher on coding benchmarks: 36.5 versus 31.4 in the Noometry coding category.
How many benchmarks do Llama 2-70B and Mistral Small 3 share?
19 benchmarks have published results for both models. Llama 2-70B has 35 scored results on Noometry and Mistral Small 3 has 24.