Model comparison
Mistral vs Phi-3.5-MoE
Mistral has enough public results to be ranked (#303); Phi-3.5-MoE does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Mistral AI
MicrosoftSummary
- Phi-3.5-MoE has downloadable open weights; the other is API-only.
Side by side
| Mistral | Phi-3.5-MoE | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 29.9 | — |
| Released | — | 2024-08-17 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Mistral: 33.8 (#250), Phi-3.5-MoE: —
| Benchmark | Mistral | Phi-3.5-MoE |
|---|---|---|
| LMArena Coding | 1162 | — |
Reasoning Not comparable
Mistral: 22.2 (#200), Phi-3.5-MoE: —
| Benchmark | Mistral | Phi-3.5-MoE |
|---|---|---|
| LMArena Hard Prompts | 1149 | — |
| PIQA | — | 88.6% |
Math Not comparable
Mistral: 22.3 (#278), Phi-3.5-MoE: —
| Benchmark | Mistral | Phi-3.5-MoE |
|---|---|---|
| Omni-MATH | 7.2% | — |
| LMArena Math | 1180 | — |
| GSM8K | — | 88.7% |
Knowledge Not comparable
Mistral: 16.6 (#288), Phi-3.5-MoE: —
| Benchmark | Mistral | Phi-3.5-MoE |
|---|---|---|
| MMLU-Pro | 27.7% | — |
| GPQA (HELM) | 30.3% | — |
| LMArena Expert | 1125 | — |
| BoolQ | — | 84.6% |
Multilingual Not comparable
Mistral: 32.8 (#254), Phi-3.5-MoE: —
| Benchmark | Mistral | Phi-3.5-MoE |
|---|---|---|
| LMArena Non-English | 1129 | — |
| LMArena Chinese | 1109 | — |
| LMArena French | 1180 | — |
| LMArena German | 1155 | — |
| LMArena Japanese | 1013 | — |
| LMArena Korean | 1032 | — |
| LMArena Russian | 1168 | — |
| LMArena Spanish | 1143 | — |
Instruction Following Not comparable
Mistral: 52.6 (#288), Phi-3.5-MoE: —
| Benchmark | Mistral | Phi-3.5-MoE |
|---|---|---|
| IFEval | 56.8% | — |
| LMArena Instruction Following | 1152 | — |
Long Context Not comparable
Mistral: 35.0 (#245), Phi-3.5-MoE: —
| Benchmark | Mistral | Phi-3.5-MoE |
|---|---|---|
| LMArena Longer Query | 1153 | — |
Writing & Preference Not comparable
Mistral: 37.0 (#260), Phi-3.5-MoE: —
| Benchmark | Mistral | Phi-3.5-MoE |
|---|---|---|
| LMArena Text | 1165 | — |
| LMArena Creative Writing | 1158 | — |
| WildBench | 66% | — |
| LMArena Multi-Turn | 1147 | — |
Frequently asked questions
Is Mistral better than Phi-3.5-MoE?
Mistral has enough public results to be ranked (#303); Phi-3.5-MoE does not yet, so treat this comparison as directional.
How many benchmarks do Mistral and Phi-3.5-MoE share?
0 benchmarks have published results for both models. Mistral has 22 scored results on Noometry and Phi-3.5-MoE has 3.