Model comparison
Llama 2-70B vs Mistral Large
Mistral Large is the stronger model overall, scoring 31.9 to 24.4 on the Noometry Index.
Last verified . 24 shared benchmarks.
Meta
Mistral AISummary
- They share 24 benchmarks with published results for both. Llama 2-70B scores higher in 0 categories and Mistral Large in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Large leads 30.1 to 7.4.
- The biggest single-benchmark swing is MATH Level 5: 3.3% for Llama 2-70B and 50.3% for Mistral Large.
Side by side
| Llama 2-70B | Mistral Large | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 24.4 | 31.9 |
| Released | 2023-07-18 | 2024-02-26 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 35 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large leads
Llama 2-70B: 31.4 (#286), Mistral Large: 34.3 (#240)
| Benchmark | Llama 2-70B | Mistral Large |
|---|---|---|
| LMArena Coding | 1079 | 1277 |
| SciCode | — | 36.2% |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| ALE-Bench | — | 264.7 |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use Not comparable
Llama 2-70B: —, Mistral Large: 28.6 (#89)
| Benchmark | Llama 2-70B | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 38.4% |
Reasoning Mistral Large leads
Llama 2-70B: 14.4 (#325), Mistral Large: 15.8 (#310)
| Benchmark | Llama 2-70B | Mistral Large |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1257 |
| DTBench | 41.6% | 65.1% |
| Epoch Capabilities Index | 113.79 | 128.52 |
| ForecastBench | 51.4 | 57.1 |
| SimpleBench | — | 22.5% |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 43.5% |
| LiveBench Data Analysis | — | 50.1% |
| LMCA | — | 16.7% |
| BIG-Bench Hard | 64.9% | — |
| CommonsenseQA 2.0 | 50% | — |
| HellaSwag | 85.3% | — |
| LAMBADA | 78.9% | — |
| LiveBench | — | 48.4% |
| PIQA | 82.8% | — |
| WinoGrande | 80.2% | — |
Math Mistral Large leads
Llama 2-70B: 8.1 (#326), Mistral Large: 18.2 (#291)
| Benchmark | Llama 2-70B | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0% | 8.5% |
| LMArena Math | 1091 | 1262 |
| MATH Level 5 | 3.3% | 50.3% |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
| GSM8K | 69.6% | — |
Knowledge Mistral Large leads
Llama 2-70B: 7.4 (#310), Mistral Large: 30.1 (#230)
| Benchmark | Llama 2-70B | Mistral Large |
|---|---|---|
| GPQA Diamond | 26.3% | 51.3% |
| LMArena Expert | 1039 | 1232 |
| MMLU | 69.9% | 80% |
| MMLU-Pro | — | 59.9% |
| Confabulations | — | 21.4% |
| Vectara Hallucination Rate | — | 4.5% |
| GPQA (HELM) | — | 43.5% |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 88.6% | — |
| OpenBookQA | 60.2% | — |
| TriviaQA | 87.6% | — |
Multilingual Mistral Large leads
Llama 2-70B: 27.7 (#274), Mistral Large: 40.0 (#219)
| Benchmark | Llama 2-70B | Mistral Large |
|---|---|---|
| LMArena Non-English | 1045 | 1237 |
| LMArena Chinese | 995 | 1240 |
| LMArena French | 1090 | 1325 |
| LMArena German | 1041 | 1254 |
| LMArena Japanese | 927 | 1188 |
| LMArena Korean | 964 | 1202 |
| LMArena Russian | 1083 | 1257 |
| LMArena Spanish | 1143 | 1268 |
Instruction Following Mistral Large leads
Llama 2-70B: 54.9 (#278), Mistral Large: 67.9 (#191)
| Benchmark | Llama 2-70B | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1071 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |
Long Context Mistral Large leads
Llama 2-70B: 32.3 (#270), Mistral Large: 38.3 (#199)
| Benchmark | Llama 2-70B | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1062 | 1261 |
Writing & Preference Mistral Large leads
Llama 2-70B: 32.3 (#279), Mistral Large: 40.7 (#242)
| Benchmark | Llama 2-70B | Mistral Large |
|---|---|---|
| LMArena Text | 1115 | 1266 |
| LMArena Creative Writing | 1075 | 1243 |
| LMArena Multi-Turn | 1088 | 1260 |
| Short-Story Creative Writing | — | 69% |
| EQ-Bench Creative Writing | — | 985 |
| WildBench | — | 80.1% |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is Llama 2-70B better than Mistral Large?
Mistral Large is the stronger model overall, scoring 31.9 to 24.4 on the Noometry Index.
Is Llama 2-70B or Mistral Large better for coding?
Mistral Large scores higher on coding benchmarks: 34.3 versus 31.4 in the Noometry coding category.
How many benchmarks do Llama 2-70B and Mistral Large share?
24 benchmarks have published results for both models. Llama 2-70B has 35 scored results on Noometry and Mistral Large has 51.