Model comparison
Mistral 7B vs Phi 3 Mini 128k Instruct
Phi 3 Mini 128k Instruct is the stronger model overall, scoring 29.7 to 23.0 on the Noometry Index.
Last verified . 18 shared benchmarks.
Mistral AI
MicrosoftSummary
- They share 18 benchmarks with published results for both. Mistral 7B scores higher in 4 categories and Phi 3 Mini 128k Instruct in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Phi 3 Mini 128k Instruct leads 31.6 to 8.1.
- The biggest single-benchmark swing is BigCodeBench Complete: 27.3% for Mistral 7B and 40.6% for Phi 3 Mini 128k Instruct.
Side by side
| Mistral 7B | Phi 3 Mini 128k Instruct | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 23.0 | 29.7 |
| 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 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Phi 3 Mini 128k Instruct leads
Mistral 7B: 26.4 (#326), Phi 3 Mini 128k Instruct: 28.8 (#312)
| Benchmark | Mistral 7B | Phi 3 Mini 128k Instruct |
|---|---|---|
| BigCodeBench Instruct | 19.5% | 29.6% |
| LMArena Coding | 1082 | 1039 |
| BigCodeBench Complete | 27.3% | 40.6% |
| HumanEval+ | 36% | — |
| MBPP+ | 42.1% | — |
Reasoning Phi 3 Mini 128k Instruct leads
Mistral 7B: 13.1 (#336), Phi 3 Mini 128k Instruct: 19.6 (#256)
| Benchmark | Mistral 7B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1067 | 1028 |
| Chess Puzzles | 0% | — |
| DTBench | 42.5% | — |
| Adversarial NLI | 47.1% | — |
| BIG-Bench Hard | 56.1% | — |
| Epoch Capabilities Index | 112.21 | — |
| HellaSwag | 81% | — |
| PIQA | 83% | — |
| WinoGrande | 75.3% | — |
Math Phi 3 Mini 128k Instruct leads
Mistral 7B: 8.1 (#325), Phi 3 Mini 128k Instruct: 31.6 (#222)
| Benchmark | Mistral 7B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Math | 1085 | 1089 |
| OTIS Mock AIME 2024-2025 | 0.3% | — |
| MATH Level 5 | 3.7% | — |
| GSM8K | 54.4% | — |
Knowledge Phi 3 Mini 128k Instruct leads
Mistral 7B: 7.4 (#311), Phi 3 Mini 128k Instruct: 26.8 (#254)
| Benchmark | Mistral 7B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Expert | 1036 | 984 |
| GPQA Diamond | 15.2% | — |
| ARC (AI2) Challenge | 78.6% | — |
| BoolQ | 87.4% | — |
| MMLU | 62.5% | — |
| OpenBookQA | 79.8% | — |
| TriviaQA | 75.2% | — |
Multilingual Too close to call
Mistral 7B: 25.8 (#283), Phi 3 Mini 128k Instruct: 25.2 (#285)
| Benchmark | Mistral 7B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Non-English | 1012 | 1000 |
| LMArena Chinese | 1009 | 1016 |
| LMArena French | 1037 | 1039 |
| LMArena German | 987 | 1006 |
| LMArena Japanese | 878 | 899 |
| LMArena Russian | 1018 | 1004 |
| LMArena Spanish | 1026 | 1059 |
| LMArena Korean | — | 856 |
Instruction Following Mistral 7B leads
Mistral 7B: 54.2 (#280), Phi 3 Mini 128k Instruct: 51.8 (#294)
| Benchmark | Mistral 7B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Instruction Following | 1060 | 1023 |
Long Context Mistral 7B leads
Mistral 7B: 32.2 (#271), Phi 3 Mini 128k Instruct: 30.4 (#289)
| Benchmark | Mistral 7B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Longer Query | 1060 | 996 |
Writing & Preference Mistral 7B leads
Mistral 7B: 30.7 (#286), Phi 3 Mini 128k Instruct: 27.1 (#301)
| Benchmark | Mistral 7B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Text | 1090 | 1050 |
| LMArena Creative Writing | 1068 | 1024 |
| LMArena Multi-Turn | 1062 | 989 |
Frequently asked questions
Is Mistral 7B better than Phi 3 Mini 128k Instruct?
Phi 3 Mini 128k Instruct is the stronger model overall, scoring 29.7 to 23.0 on the Noometry Index.
Is Mistral 7B or Phi 3 Mini 128k Instruct better for coding?
Phi 3 Mini 128k Instruct scores higher on coding benchmarks: 28.8 versus 26.4 in the Noometry coding category.
How many benchmarks do Mistral 7B and Phi 3 Mini 128k Instruct share?
18 benchmarks have published results for both models. Mistral 7B has 37 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.