Model comparison
Llama 2-70B vs Mistral Nemo
Mistral Nemo is the stronger model overall, scoring 26.4 to 24.4 on the Noometry Index.
Last verified . 7 shared benchmarks.
Meta
Mistral AISummary
- They share 7 benchmarks with published results for both. Llama 2-70B scores higher in 1 category and Mistral Nemo in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral Nemo leads 25.5 to 8.1.
- The biggest single-benchmark swing is MATH Level 5: 3.3% for Llama 2-70B and 10.8% for Mistral Nemo.
Side by side
| Llama 2-70B | Mistral Nemo | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 24.4 | 26.4 |
| Released | 2023-07-18 | 2024-07-01 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.15 |
| Results tracked | 35 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 2-70B: 31.4 (#286), Mistral Nemo: —
| Benchmark | Llama 2-70B | Mistral Nemo |
|---|---|---|
| LMArena Coding | 1079 | — |
Agentic & Tool Use Not comparable
Llama 2-70B: —, Mistral Nemo: 23.5 (#125)
| Benchmark | Llama 2-70B | Mistral Nemo |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 27.6% |
| BALROG | — | 17.6% |
Reasoning Mistral Nemo leads
Llama 2-70B: 14.4 (#325), Mistral Nemo: 20.7 (#232)
| Benchmark | Llama 2-70B | Mistral Nemo |
|---|---|---|
| DTBench | 41.6% | 48.6% |
| Epoch Capabilities Index | 113.79 | 118.68 |
| PIQA | 82.8% | 83.5% |
| LMArena Hard Prompts | 1073 | — |
| BIG-Bench Hard | 64.9% | — |
| CommonsenseQA 2.0 | 50% | — |
| ForecastBench | 51.4 | — |
| HellaSwag | 85.3% | — |
| LAMBADA | 78.9% | — |
| WinoGrande | 80.2% | — |
Math Mistral Nemo leads
Llama 2-70B: 8.1 (#326), Mistral Nemo: 25.5 (#268)
| Benchmark | Llama 2-70B | Mistral Nemo |
|---|---|---|
| MATH Level 5 | 3.3% | 10.8% |
| GSM8K | 69.6% | 84.2% |
| OTIS Mock AIME 2024-2025 | 0% | — |
| LMArena Math | 1091 | — |
Knowledge Mistral Nemo leads
Llama 2-70B: 7.4 (#310), Mistral Nemo: 12.3 (#298)
| Benchmark | Llama 2-70B | Mistral Nemo |
|---|---|---|
| GPQA Diamond | 26.3% | 29.9% |
| BoolQ | 88.6% | 82.5% |
| LMArena Expert | 1039 | — |
| ARC (AI2) Challenge | 78.3% | — |
| MMLU | 69.9% | — |
| OpenBookQA | 60.2% | — |
| TriviaQA | 87.6% | — |
Multilingual Not comparable
Llama 2-70B: 27.7 (#274), Mistral Nemo: —
| Benchmark | Llama 2-70B | Mistral Nemo |
|---|---|---|
| LMArena Non-English | 1045 | — |
| LMArena Chinese | 995 | — |
| LMArena French | 1090 | — |
| LMArena German | 1041 | — |
| LMArena Japanese | 927 | — |
| LMArena Korean | 964 | — |
| LMArena Russian | 1083 | — |
| LMArena Spanish | 1143 | — |
Instruction Following Not comparable
Llama 2-70B: 54.9 (#278), Mistral Nemo: —
| Benchmark | Llama 2-70B | Mistral Nemo |
|---|---|---|
| LMArena Instruction Following | 1071 | — |
Long Context Not comparable
Llama 2-70B: 32.3 (#270), Mistral Nemo: —
| Benchmark | Llama 2-70B | Mistral Nemo |
|---|---|---|
| LMArena Longer Query | 1062 | — |
Writing & Preference Llama 2-70B leads
Llama 2-70B: 32.3 (#279), Mistral Nemo: 28.5 (#296)
| Benchmark | Llama 2-70B | Mistral Nemo |
|---|---|---|
| LMArena Text | 1115 | — |
| LMArena Creative Writing | 1075 | — |
| EQ-Bench Creative Writing | — | 881 |
| LMArena Multi-Turn | 1088 | — |
Frequently asked questions
Is Llama 2-70B better than Mistral Nemo?
Mistral Nemo is the stronger model overall, scoring 26.4 to 24.4 on the Noometry Index.
How many benchmarks do Llama 2-70B and Mistral Nemo share?
7 benchmarks have published results for both models. Llama 2-70B has 35 scored results on Noometry and Mistral Nemo has 10.