Model comparison
Mistral 7B vs Phi 3 Small 8k Instruct
Phi 3 Small 8k Instruct is the stronger model overall, scoring 29.3 to 23.0 on the Noometry Index.
Last verified . 24 shared benchmarks.
Mistral AI
MicrosoftSummary
- They share 24 benchmarks with published results for both. Mistral 7B scores higher in 1 category and Phi 3 Small 8k Instruct in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Phi 3 Small 8k Instruct leads 29.1 to 7.4.
Side by side
| Mistral 7B | Phi 3 Small 8k Instruct | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 23.0 | 29.3 |
| 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 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Phi 3 Small 8k Instruct leads
Mistral 7B: 26.4 (#326), Phi 3 Small 8k Instruct: 27.9 (#318)
| Benchmark | Mistral 7B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1082 | 1101 |
| BigCodeBench Instruct | 19.5% | — |
| LiveBench Coding | — | 20.3% |
| BigCodeBench Complete | 27.3% | — |
| HumanEval+ | 36% | — |
| MBPP+ | 42.1% | — |
Reasoning Phi 3 Small 8k Instruct leads
Mistral 7B: 13.1 (#336), Phi 3 Small 8k Instruct: 14.8 (#323)
| Benchmark | Mistral 7B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1067 | 1100 |
| Adversarial NLI | 47.1% | 58.1% |
| BIG-Bench Hard | 56.1% | 79.1% |
| HellaSwag | 81% | 77% |
| WinoGrande | 75.3% | 81.5% |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | — | 15.9% |
| DTBench | 42.5% | — |
| LiveBench Data Analysis | — | 30.3% |
| Epoch Capabilities Index | 112.21 | — |
| LiveBench | — | 24% |
| PIQA | 83% | — |
Math Phi 3 Small 8k Instruct leads
Mistral 7B: 8.1 (#325), Phi 3 Small 8k Instruct: 27.6 (#248)
| Benchmark | Mistral 7B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1085 | 1151 |
| OTIS Mock AIME 2024-2025 | 0.3% | — |
| LiveBench Math | — | 17.6% |
| MATH Level 5 | 3.7% | — |
| GSM8K | 54.4% | — |
Knowledge Phi 3 Small 8k Instruct leads
Mistral 7B: 7.4 (#311), Phi 3 Small 8k Instruct: 29.1 (#240)
| Benchmark | Mistral 7B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1036 | 1067 |
| ARC (AI2) Challenge | 78.6% | 90.7% |
| MMLU | 62.5% | 75.7% |
| OpenBookQA | 79.8% | 88% |
| TriviaQA | 75.2% | 58.1% |
| GPQA Diamond | 15.2% | — |
| BoolQ | 87.4% | — |
Multilingual Phi 3 Small 8k Instruct leads
Mistral 7B: 25.8 (#283), Phi 3 Small 8k Instruct: 28.5 (#272)
| Benchmark | Mistral 7B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1012 | 1058 |
| LMArena Chinese | 1009 | 1061 |
| LMArena French | 1037 | 1135 |
| LMArena German | 987 | 1080 |
| LMArena Japanese | 878 | 966 |
| LMArena Russian | 1018 | 1111 |
| LMArena Spanish | 1026 | 1111 |
| LMArena Korean | — | 894 |
Instruction Following Mistral 7B leads
Mistral 7B: 54.2 (#280), Phi 3 Small 8k Instruct: 51.9 (#292)
| Benchmark | Mistral 7B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 1060 | 1087 |
| LiveBench Instruction Following | — | 47.2% |
Long Context Too close to call
Mistral 7B: 32.2 (#271), Phi 3 Small 8k Instruct: 33.0 (#267)
| Benchmark | Mistral 7B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1060 | 1088 |
Writing & Preference Too close to call
Mistral 7B: 30.7 (#286), Phi 3 Small 8k Instruct: 31.1 (#284)
| Benchmark | Mistral 7B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1090 | 1110 |
| LMArena Creative Writing | 1068 | 1083 |
| LMArena Multi-Turn | 1062 | 1068 |
| LiveBench Language | — | 12.9% |
Frequently asked questions
Is Mistral 7B better than Phi 3 Small 8k Instruct?
Phi 3 Small 8k Instruct is the stronger model overall, scoring 29.3 to 23.0 on the Noometry Index.
Is Mistral 7B or Phi 3 Small 8k Instruct better for coding?
Phi 3 Small 8k Instruct scores higher on coding benchmarks: 27.9 versus 26.4 in the Noometry coding category.
How many benchmarks do Mistral 7B and Phi 3 Small 8k Instruct share?
24 benchmarks have published results for both models. Mistral 7B has 37 scored results on Noometry and Phi 3 Small 8k Instruct has 32.