Model comparison
Mistral vs Phi 3 Medium 4k Instruct
Phi 3 Medium 4k Instruct is the stronger model overall, scoring 32.4 to 29.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AI
MicrosoftSummary
- They share 17 benchmarks with published results for both. Mistral scores higher in 5 categories and Phi 3 Medium 4k Instruct in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Phi 3 Medium 4k Instruct leads 29.6 to 16.3.
- Phi 3 Medium 4k Instruct has downloadable open weights; the other is API-only.
Side by side
| Mistral | Phi 3 Medium 4k Instruct | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 29.4 | 32.4 |
| Released | — | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Mistral: 33.2 (#249), Phi 3 Medium 4k Instruct: 32.3 (#263)
| Benchmark | Mistral | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Coding | 1162 | 1130 |
Reasoning Too close to call
Mistral: 21.3 (#199), Phi 3 Medium 4k Instruct: 20.8 (#214)
| Benchmark | Mistral | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1149 | 1127 |
Math Phi 3 Medium 4k Instruct leads
Mistral: 20.5 (#275), Phi 3 Medium 4k Instruct: 30.9 (#202)
| Benchmark | Mistral | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Math | 1180 | 1173 |
| Omni-MATH | 7.2% | — |
Knowledge Phi 3 Medium 4k Instruct leads
Mistral: 16.3 (#283), Phi 3 Medium 4k Instruct: 29.6 (#226)
| Benchmark | Mistral | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Expert | 1125 | 1108 |
| MMLU-Pro | 27.7% | — |
| GPQA (HELM) | 30.3% | — |
Multilingual Mistral leads
Mistral: 33.0 (#249), Phi 3 Medium 4k Instruct: 30.8 (#258)
| Benchmark | Mistral | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | 1129 | 1094 |
| LMArena Chinese | 1109 | 1108 |
| LMArena French | 1179 | 1109 |
| LMArena German | 1155 | 1101 |
| LMArena Japanese | 1012 | 1042 |
| LMArena Korean | 1032 | 954 |
| LMArena Russian | 1168 | 1145 |
| LMArena Spanish | 1143 | 1095 |
Instruction Following Phi 3 Medium 4k Instruct leads
Mistral: 52.9 (#283), Phi 3 Medium 4k Instruct: 57.8 (#263)
| Benchmark | Mistral | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1152 | 1114 |
| IFEval | 56.8% | — |
Long Context Mistral leads
Mistral: 35.0 (#240), Phi 3 Medium 4k Instruct: 33.9 (#250)
| Benchmark | Mistral | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1154 | 1120 |
Writing & Preference Mistral leads
Mistral: 37.2 (#255), Phi 3 Medium 4k Instruct: 34.3 (#267)
| Benchmark | Mistral | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | 1165 | 1138 |
| LMArena Creative Writing | 1158 | 1106 |
| LMArena Multi-Turn | 1147 | 1088 |
| WildBench | 66% | — |
Frequently asked questions
Is Mistral better than Phi 3 Medium 4k Instruct?
Phi 3 Medium 4k Instruct is the stronger model overall, scoring 32.4 to 29.4 on the Noometry Index.
Is Mistral or Phi 3 Medium 4k Instruct better for coding?
They score almost the same on coding (33.2 vs 32.3); test both on your own repository before choosing.
How many benchmarks do Mistral and Phi 3 Medium 4k Instruct share?
17 benchmarks have published results for both models. Mistral has 22 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.