Model comparison
Llama 2-70B vs Mistral Small
Mistral Small is the stronger model overall, scoring 33.4 to 24.4 on the Noometry Index.
Last verified . 22 shared benchmarks.
Meta
Mistral AISummary
- They share 22 benchmarks with published results for both. Llama 2-70B scores higher in 0 categories and Mistral Small in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Small leads 31.0 to 7.4.
- The biggest single-benchmark swing is MATH Level 5: 3.3% for Llama 2-70B and 46.8% for Mistral Small.
Side by side
| Llama 2-70B | Mistral Small | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 24.4 | 33.4 |
| Released | 2023-07-18 | 2024-02-26 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 256K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.60 |
| Results tracked | 35 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small leads
Llama 2-70B: 31.4 (#286), Mistral Small: 34.0 (#247)
| Benchmark | Llama 2-70B | Mistral Small |
|---|---|---|
| LMArena Coding | 1079 | 1362 |
| SciCode | — | 26.5% |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
| ALE-Bench | — | 497.62 |
Agentic & Tool Use Not comparable
Llama 2-70B: —, Mistral Small: 28.1 (#93)
| Benchmark | Llama 2-70B | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |
Reasoning Mistral Small leads
Llama 2-70B: 14.4 (#325), Mistral Small: 19.8 (#250)
| Benchmark | Llama 2-70B | Mistral Small |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1335 |
| DTBench | 41.6% | 70.9% |
| Kagi LLM Benchmark | — | 37.8% |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 44.8% |
| LiveBench Data Analysis | — | 53.7% |
| LMCA | — | 20.6% |
| BIG-Bench Hard | 64.9% | — |
| CommonsenseQA 2.0 | 50% | — |
| Epoch Capabilities Index | 113.79 | — |
| ForecastBench | 51.4 | — |
| HellaSwag | 85.3% | — |
| LAMBADA | 78.9% | — |
| LiveBench | — | 44% |
| PIQA | 82.8% | — |
| WinoGrande | 80.2% | — |
Math Mistral Small leads
Llama 2-70B: 8.1 (#326), Mistral Small: 16.4 (#293)
| Benchmark | Llama 2-70B | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0% | 5.8% |
| LMArena Math | 1091 | 1341 |
| MATH Level 5 | 3.3% | 46.8% |
| LiveBench Math | — | 39.9% |
| GSM8K | 69.6% | — |
Knowledge Mistral Small leads
Llama 2-70B: 7.4 (#310), Mistral Small: 31.0 (#222)
| Benchmark | Llama 2-70B | Mistral Small |
|---|---|---|
| GPQA Diamond | 26.3% | 47.5% |
| LMArena Expert | 1039 | 1291 |
| MMLU | 69.9% | 68.7% |
| Vectara Hallucination Rate | — | 5.1% |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 88.6% | — |
| OpenBookQA | 60.2% | — |
| TriviaQA | 87.6% | — |
Multimodal Not comparable
Llama 2-70B: —, Mistral Small: 33.5 (#96)
| Benchmark | Llama 2-70B | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |
Multilingual Mistral Small leads
Llama 2-70B: 27.7 (#274), Mistral Small: 45.5 (#169)
| Benchmark | Llama 2-70B | Mistral Small |
|---|---|---|
| LMArena Non-English | 1045 | 1315 |
| LMArena Chinese | 995 | 1340 |
| LMArena French | 1090 | 1337 |
| LMArena German | 1041 | 1340 |
| LMArena Japanese | 927 | 1275 |
| LMArena Korean | 964 | 1259 |
| LMArena Russian | 1083 | 1324 |
| LMArena Spanish | 1143 | 1346 |
Instruction Following Mistral Small leads
Llama 2-70B: 54.9 (#278), Mistral Small: 66.4 (#209)
| Benchmark | Llama 2-70B | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1071 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
Long Context Mistral Small leads
Llama 2-70B: 32.3 (#270), Mistral Small: 40.4 (#156)
| Benchmark | Llama 2-70B | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1062 | 1327 |
Writing & Preference Mistral Small leads
Llama 2-70B: 32.3 (#279), Mistral Small: 52.5 (#171)
| Benchmark | Llama 2-70B | Mistral Small |
|---|---|---|
| LMArena Text | 1115 | 1338 |
| LMArena Creative Writing | 1075 | 1305 |
| LMArena Multi-Turn | 1088 | 1344 |
| LiveBench Language | — | 30.5% |
Frequently asked questions
Is Llama 2-70B better than Mistral Small?
Mistral Small is the stronger model overall, scoring 33.4 to 24.4 on the Noometry Index.
Is Llama 2-70B or Mistral Small better for coding?
Mistral Small scores higher on coding benchmarks: 34.0 versus 31.4 in the Noometry coding category.
How many benchmarks do Llama 2-70B and Mistral Small share?
22 benchmarks have published results for both models. Llama 2-70B has 35 scored results on Noometry and Mistral Small has 39.