Model comparison
Mistral vs Phi-4
Phi-4 is the stronger model overall, scoring 31.2 to 29.9 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 2 categories and Phi-4 in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Phi-4 leads 32.6 to 16.6.
- Phi-4 has downloadable open weights; the other is API-only.
Side by side
| Mistral | Phi-4 | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 29.9 | 31.2 |
| Released | — | 2024-12-11 |
| Weights | Proprietary | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.07 |
| Output $ / M tokens | — | $0.14 |
| Results tracked | 22 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Mistral: 33.8 (#250), Phi-4: 34.4 (#239)
| Benchmark | Mistral | Phi-4 |
|---|---|---|
| LMArena Coding | 1162 | 1231 |
| BigCodeBench Instruct | — | 45.5% |
| LiveBench Coding | — | 30.7% |
| BigCodeBench Complete | — | 55.4% |
Agentic & Tool Use Not comparable
Mistral: —, Phi-4: 22.8 (#128)
| Benchmark | Mistral | Phi-4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.8% |
| BALROG | — | 11.6% |
Reasoning Mistral leads
Mistral: 22.2 (#200), Phi-4: 17.7 (#291)
| Benchmark | Mistral | Phi-4 |
|---|---|---|
| LMArena Hard Prompts | 1149 | 1220 |
| Chess Puzzles | — | 1% |
| LiveBench Reasoning | — | 47.8% |
| LiveBench Data Analysis | — | 45.2% |
| Epoch Capabilities Index | — | 130.42 |
| LiveBench | — | 41.6% |
Math Mistral leads
Mistral: 22.3 (#278), Phi-4: 20.8 (#285)
| Benchmark | Mistral | Phi-4 |
|---|---|---|
| LMArena Math | 1180 | 1246 |
| OTIS Mock AIME 2024-2025 | — | 13.8% |
| Omni-MATH | 7.2% | — |
| LiveBench Math | — | 42% |
| MATH Level 5 | — | 64.9% |
Knowledge Phi-4 leads
Mistral: 16.6 (#288), Phi-4: 32.6 (#209)
| Benchmark | Mistral | Phi-4 |
|---|---|---|
| LMArena Expert | 1125 | 1203 |
| GPQA Diamond | — | 56.1% |
| MMLU-Pro | 27.7% | — |
| Confabulations | — | 29.4% |
| Vectara Hallucination Rate | — | 3.7% |
| GPQA (HELM) | 30.3% | — |
| MMLU | — | 84.8% |
Multilingual Phi-4 leads
Mistral: 32.8 (#254), Phi-4: 37.2 (#237)
| Benchmark | Mistral | Phi-4 |
|---|---|---|
| LMArena Non-English | 1129 | 1197 |
| LMArena Chinese | 1109 | 1212 |
| LMArena French | 1180 | 1224 |
| LMArena German | 1155 | 1222 |
| LMArena Japanese | 1013 | 1158 |
| LMArena Korean | 1032 | 1151 |
| LMArena Russian | 1168 | 1209 |
| LMArena Spanish | 1143 | 1234 |
Instruction Following Phi-4 leads
Mistral: 52.6 (#288), Phi-4: 60.4 (#251)
| Benchmark | Mistral | Phi-4 |
|---|---|---|
| LMArena Instruction Following | 1152 | 1201 |
| LiveBench Instruction Following | — | 58.4% |
| IFEval | 56.8% | — |
Long Context Phi-4 leads
Mistral: 35.0 (#245), Phi-4: 36.9 (#226)
| Benchmark | Mistral | Phi-4 |
|---|---|---|
| LMArena Longer Query | 1153 | 1217 |
Writing & Preference Phi-4 leads
Mistral: 37.0 (#260), Phi-4: 40.5 (#244)
| Benchmark | Mistral | Phi-4 |
|---|---|---|
| LMArena Text | 1165 | 1217 |
| LMArena Creative Writing | 1158 | 1182 |
| LMArena Multi-Turn | 1147 | 1206 |
| Short-Story Creative Writing | — | 62.6% |
| WildBench | 66% | — |
| LiveBench Language | — | 25.6% |
Frequently asked questions
Is Mistral better than Phi-4?
Phi-4 is the stronger model overall, scoring 31.2 to 29.9 on the Noometry Index.
Is Mistral or Phi-4 better for coding?
They score almost the same on coding (33.8 vs 34.4); test both on your own repository before choosing.
How many benchmarks do Mistral and Phi-4 share?
17 benchmarks have published results for both models. Mistral has 22 scored results on Noometry and Phi-4 has 37.