Model comparison
Llama 2-7B vs Mistral Medium 3.5
Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 29.1 on the Noometry Index.
Last verified . 16 shared benchmarks.
Meta
Mistral AISummary
- They share 16 benchmarks with published results for both. Llama 2-7B scores higher in 0 categories and Mistral Medium 3.5 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium 3.5 leads 58.5 to 28.0.
Side by side
| Llama 2-7B | Mistral Medium 3.5 | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 29.1 | 40.2 |
| Released | 2023-07-18 | — |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 210K |
| Input $ / M tokens | — | $1.50 |
| Output $ / M tokens | — | $7.50 |
| Results tracked | 29 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Medium 3.5 leads
Llama 2-7B: 29.2 (#307), Mistral Medium 3.5: 36.0 (#213)
| Benchmark | Llama 2-7B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Coding | 1002 | 1461 |
| LMArena WebDev | — | 1264 |
Reasoning Mistral Medium 3.5 leads
Llama 2-7B: 15.7 (#312), Mistral Medium 3.5: 17.3 (#295)
| Benchmark | Llama 2-7B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Hard Prompts | 1009 | 1436 |
| Epoch Capabilities Index | 99.06 | 141.35 |
| Kagi LLM Benchmark | — | 41.4% |
| NYT Connections (extended) | — | 12.9% |
| Chess Puzzles | 0% | — |
| BIG-Bench Hard | 39.2% | — |
| HellaSwag | 77.2% | — |
| LAMBADA | 73.3% | — |
| PIQA | 78.8% | — |
| WinoGrande | 69.2% | — |
Math Mistral Medium 3.5 leads
Llama 2-7B: 30.7 (#233), Mistral Medium 3.5: 39.1 (#113)
| Benchmark | Llama 2-7B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Math | 1042 | 1431 |
| GSM8K | 16.7% | — |
Knowledge Mistral Medium 3.5 leads
Llama 2-7B: 28.2 (#248), Mistral Medium 3.5: 40.0 (#126)
| Benchmark | Llama 2-7B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Expert | 1036 | 1432 |
| ARC (AI2) Challenge | 45.9% | — |
| BoolQ | 77.9% | — |
| MMLU | 45.8% | — |
| OpenBookQA | 58.6% | — |
| TriviaQA | 73.7% | — |
Multimodal Not comparable
Llama 2-7B: —, Mistral Medium 3.5: 38.3 (#65)
| Benchmark | Llama 2-7B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Vision | — | 1223 |
| ScienceQA | 43.1% | — |
Multilingual Mistral Medium 3.5 leads
Llama 2-7B: 23.8 (#293), Mistral Medium 3.5: 51.9 (#100)
| Benchmark | Llama 2-7B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Non-English | 973 | 1404 |
| LMArena Chinese | 973 | 1442 |
| LMArena French | 970 | 1448 |
| LMArena German | 978 | 1451 |
| LMArena Russian | 995 | 1395 |
| LMArena Spanish | 1007 | 1409 |
| LMArena Korean | — | 1385 |
Instruction Following Mistral Medium 3.5 leads
Llama 2-7B: 50.8 (#298), Mistral Medium 3.5: 74.6 (#90)
| Benchmark | Llama 2-7B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Instruction Following | 1006 | 1415 |
Long Context Mistral Medium 3.5 leads
Llama 2-7B: 30.4 (#287), Mistral Medium 3.5: 43.2 (#103)
| Benchmark | Llama 2-7B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Longer Query | 999 | 1415 |
Writing & Preference Mistral Medium 3.5 leads
Llama 2-7B: 28.0 (#298), Mistral Medium 3.5: 58.5 (#117)
| Benchmark | Llama 2-7B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Text | 1053 | 1421 |
| LMArena Creative Writing | 1033 | 1374 |
| LMArena Multi-Turn | 1029 | 1423 |
| EQ-Bench 4 | — | 993 |
Frequently asked questions
Is Llama 2-7B better than Mistral Medium 3.5?
Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 29.1 on the Noometry Index.
Is Llama 2-7B or Mistral Medium 3.5 better for coding?
Mistral Medium 3.5 scores higher on coding benchmarks: 36.0 versus 29.2 in the Noometry coding category.
How many benchmarks do Llama 2-7B and Mistral Medium 3.5 share?
16 benchmarks have published results for both models. Llama 2-7B has 29 scored results on Noometry and Mistral Medium 3.5 has 22.