Model comparison
Mistral 7B vs Phi-2
Mistral 7B has enough public results to be ranked (#351); Phi-2 does not yet, so treat this comparison as directional.
Last verified . 11 shared benchmarks.
Mistral AI
MicrosoftSummary
- They share 11 benchmarks with published results for both.
Side by side
| Mistral 7B | Phi-2 | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 23.0 | — |
| Released | 2023-09-27 | 2023-12-12 |
| Weights | Open | Open |
| Context window | 8K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.25 | — |
| Results tracked | 37 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Mistral 7B: 26.4 (#326), Phi-2: —
| Benchmark | Mistral 7B | Phi-2 |
|---|---|---|
| HumanEval+ | 36% | 45.1% |
| MBPP+ | 42.1% | 54.2% |
| BigCodeBench Instruct | 19.5% | — |
| LMArena Coding | 1082 | — |
| BigCodeBench Complete | 27.3% | — |
Reasoning Not comparable
Mistral 7B: 13.1 (#336), Phi-2: —
| Benchmark | Mistral 7B | Phi-2 |
|---|---|---|
| Adversarial NLI | 47.1% | 42.5% |
| BIG-Bench Hard | 56.1% | 59.4% |
| Epoch Capabilities Index | 112.21 | 107.94 |
| HellaSwag | 81% | 53.6% |
| WinoGrande | 75.3% | 54.7% |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1067 | — |
| DTBench | 42.5% | — |
| PIQA | 83% | — |
Math Not comparable
Mistral 7B: 8.1 (#325), Phi-2: —
| Benchmark | Mistral 7B | Phi-2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.3% | — |
| LMArena Math | 1085 | — |
| MATH Level 5 | 3.7% | — |
| GSM8K | 54.4% | — |
Knowledge Not comparable
Mistral 7B: 7.4 (#311), Phi-2: —
| Benchmark | Mistral 7B | Phi-2 |
|---|---|---|
| ARC (AI2) Challenge | 78.6% | 75.9% |
| MMLU | 62.5% | 58.4% |
| OpenBookQA | 79.8% | 73.6% |
| TriviaQA | 75.2% | 45.2% |
| GPQA Diamond | 15.2% | — |
| LMArena Expert | 1036 | — |
| BoolQ | 87.4% | — |
Multilingual Not comparable
Mistral 7B: 25.8 (#283), Phi-2: —
| Benchmark | Mistral 7B | Phi-2 |
|---|---|---|
| LMArena Non-English | 1012 | — |
| LMArena Chinese | 1009 | — |
| LMArena French | 1037 | — |
| LMArena German | 987 | — |
| LMArena Japanese | 878 | — |
| LMArena Russian | 1018 | — |
| LMArena Spanish | 1026 | — |
Instruction Following Not comparable
Mistral 7B: 54.2 (#280), Phi-2: —
| Benchmark | Mistral 7B | Phi-2 |
|---|---|---|
| LMArena Instruction Following | 1060 | — |
Long Context Not comparable
Mistral 7B: 32.2 (#271), Phi-2: —
| Benchmark | Mistral 7B | Phi-2 |
|---|---|---|
| LMArena Longer Query | 1060 | — |
Writing & Preference Not comparable
Mistral 7B: 30.7 (#286), Phi-2: —
| Benchmark | Mistral 7B | Phi-2 |
|---|---|---|
| LMArena Text | 1090 | — |
| LMArena Creative Writing | 1068 | — |
| LMArena Multi-Turn | 1062 | — |
Frequently asked questions
Is Mistral 7B better than Phi-2?
Mistral 7B has enough public results to be ranked (#351); Phi-2 does not yet, so treat this comparison as directional.
How many benchmarks do Mistral 7B and Phi-2 share?
11 benchmarks have published results for both models. Mistral 7B has 37 scored results on Noometry and Phi-2 has 11.