Model comparison
Mistral 7B vs phi-3-medium 14B
phi-3-medium 14B is the stronger model overall, scoring 29.1 to 22.9 on the Noometry Index.
Last verified . 13 shared benchmarks.
Mistral AI
MicrosoftSummary
- They share 13 benchmarks with published results for both. Mistral 7B scores higher in 0 categories and phi-3-medium 14B in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where phi-3-medium 14B leads 25.2 to 7.6.
- The biggest single-benchmark swing is BigCodeBench Complete: 27.3% for Mistral 7B and 48.7% for phi-3-medium 14B.
Side by side
| Mistral 7B | phi-3-medium 14B | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 22.9 | 29.1 |
| Released | 2023-09-27 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 8K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.25 | — |
| Results tracked | 37 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding phi-3-medium 14B leads
Mistral 7B: 25.9 (#321), phi-3-medium 14B: 36.3 (#198)
| Benchmark | Mistral 7B | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | 19.5% | 37.6% |
| BigCodeBench Complete | 27.3% | 48.7% |
| LMArena Coding | 1082 | — |
| HumanEval+ | 36% | — |
| MBPP+ | 42.1% | — |
Reasoning Not comparable
Mistral 7B: 12.6 (#331), phi-3-medium 14B: —
| Benchmark | Mistral 7B | phi-3-medium 14B |
|---|---|---|
| Adversarial NLI | 47.1% | 55.8% |
| BIG-Bench Hard | 56.1% | 81.4% |
| Epoch Capabilities Index | 111.97 | 121.18 |
| HellaSwag | 81% | 82.4% |
| WinoGrande | 75.3% | 81.5% |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1067 | — |
| DTBench | 42.5% | — |
| PIQA | 83% | — |
Math phi-3-medium 14B leads
Mistral 7B: 7.6 (#319), phi-3-medium 14B: 25.2 (#249)
| Benchmark | Mistral 7B | phi-3-medium 14B |
|---|---|---|
| MATH Level 5 | 3.7% | 17.6% |
| OTIS Mock AIME 2024-2025 | 0.3% | — |
| LMArena Math | 1085 | — |
| GSM8K | 54.4% | — |
Knowledge phi-3-medium 14B leads
Mistral 7B: 7.3 (#306), phi-3-medium 14B: 9.1 (#301)
| Benchmark | Mistral 7B | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | 15.2% | 27.6% |
| ARC (AI2) Challenge | 78.6% | 91.6% |
| MMLU | 62.5% | 78% |
| OpenBookQA | 79.8% | 87.4% |
| TriviaQA | 75.2% | 73.9% |
| LMArena Expert | 1036 | — |
| BoolQ | 87.4% | — |
Multilingual Not comparable
Mistral 7B: 26.0 (#278), phi-3-medium 14B: —
| Benchmark | Mistral 7B | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1012 | — |
| LMArena Chinese | 1009 | — |
| LMArena French | 1036 | — |
| LMArena German | 987 | — |
| LMArena Japanese | 878 | — |
| LMArena Russian | 1018 | — |
| LMArena Spanish | 1026 | — |
Instruction Following Not comparable
Mistral 7B: 54.5 (#275), phi-3-medium 14B: —
| Benchmark | Mistral 7B | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1060 | — |
Long Context Not comparable
Mistral 7B: 32.2 (#266), phi-3-medium 14B: —
| Benchmark | Mistral 7B | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1060 | — |
Writing & Preference Not comparable
Mistral 7B: 30.9 (#281), phi-3-medium 14B: —
| Benchmark | Mistral 7B | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1090 | — |
| LMArena Creative Writing | 1068 | — |
| LMArena Multi-Turn | 1062 | — |
Frequently asked questions
Is Mistral 7B better than phi-3-medium 14B?
phi-3-medium 14B is the stronger model overall, scoring 29.1 to 22.9 on the Noometry Index.
Is Mistral 7B or phi-3-medium 14B better for coding?
phi-3-medium 14B scores higher on coding benchmarks: 36.3 versus 25.9 in the Noometry coding category.
How many benchmarks do Mistral 7B and phi-3-medium 14B share?
13 benchmarks have published results for both models. Mistral 7B has 37 scored results on Noometry and phi-3-medium 14B has 13.