Model comparison
Mistral Small 3.2 vs Phi-4
Mistral Small 3.2 and Phi-4 score almost the same on the Noometry Index (31.2 vs 31.2), so choose on price, context window or the category you care about most.
Last verified . 4 shared benchmarks.
Mistral AI
MicrosoftSummary
- They share 4 benchmarks with published results for both. Mistral Small 3.2 scores higher in 3 categories and Phi-4 in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Phi-4 leads 32.6 to 26.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 30.3% for Mistral Small 3.2 and 13.8% for Phi-4.
- Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $0.0938 / $0.25 for Mistral Small 3.2.
- Mistral Small 3.2 accepts more context: 256K tokens versus 128K.
Side by side
| Mistral Small 3.2 | Phi-4 | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 31.2 | 31.2 |
| Released | 2025-06-20 | 2024-12-11 |
| Weights | Open | Open |
| Context window | 256K | 128K |
| Max output | 16K | 4K |
| Input $ / M tokens | $0.0938 | $0.07 |
| Output $ / M tokens | $0.25 | $0.14 |
| Results tracked | 6 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Mistral Small 3.2: —, Phi-4: 34.4 (#239)
| Benchmark | Mistral Small 3.2 | Phi-4 |
|---|---|---|
| BigCodeBench Instruct | — | 45.5% |
| LiveBench Coding | — | 30.7% |
| LMArena Coding | — | 1231 |
| BigCodeBench Complete | — | 55.4% |
Agentic & Tool Use Not comparable
Mistral Small 3.2: —, Phi-4: 22.8 (#128)
| Benchmark | Mistral Small 3.2 | Phi-4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.8% |
| BALROG | — | 11.6% |
Reasoning Too close to call
Mistral Small 3.2: 18.1 (#287), Phi-4: 17.7 (#291)
| Benchmark | Mistral Small 3.2 | Phi-4 |
|---|---|---|
| Chess Puzzles | 1% | 1% |
| Epoch Capabilities Index | 131.74 | 130.42 |
| Kagi LLM Benchmark | 40.4% | — |
| LiveBench Reasoning | — | 47.8% |
| LMArena Hard Prompts | — | 1220 |
| LiveBench Data Analysis | — | 45.2% |
| LiveBench | — | 41.6% |
Math Mistral Small 3.2 leads
Mistral Small 3.2: 26.3 (#260), Phi-4: 20.8 (#285)
| Benchmark | Mistral Small 3.2 | Phi-4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 30.3% | 13.8% |
| LiveBench Math | — | 42% |
| LMArena Math | — | 1246 |
| MATH Level 5 | — | 64.9% |
Knowledge Phi-4 leads
Mistral Small 3.2: 26.7 (#256), Phi-4: 32.6 (#209)
| Benchmark | Mistral Small 3.2 | Phi-4 |
|---|---|---|
| GPQA Diamond | 49.1% | 56.1% |
| Confabulations | — | 29.4% |
| Vectara Hallucination Rate | — | 3.7% |
| LMArena Expert | — | 1203 |
| MMLU | — | 84.8% |
Multilingual Not comparable
Mistral Small 3.2: —, Phi-4: 37.2 (#237)
| Benchmark | Mistral Small 3.2 | Phi-4 |
|---|---|---|
| LMArena Non-English | — | 1197 |
| LMArena Chinese | — | 1212 |
| LMArena French | — | 1224 |
| LMArena German | — | 1222 |
| LMArena Japanese | — | 1158 |
| LMArena Korean | — | 1151 |
| LMArena Russian | — | 1209 |
| LMArena Spanish | — | 1234 |
Instruction Following Not comparable
Mistral Small 3.2: —, Phi-4: 60.4 (#251)
| Benchmark | Mistral Small 3.2 | Phi-4 |
|---|---|---|
| LiveBench Instruction Following | — | 58.4% |
| LMArena Instruction Following | — | 1201 |
Long Context Not comparable
Mistral Small 3.2: —, Phi-4: 36.9 (#226)
| Benchmark | Mistral Small 3.2 | Phi-4 |
|---|---|---|
| LMArena Longer Query | — | 1217 |
Writing & Preference Mistral Small 3.2 leads
Mistral Small 3.2: 45.0 (#224), Phi-4: 40.5 (#244)
| Benchmark | Mistral Small 3.2 | Phi-4 |
|---|---|---|
| LMArena Text | — | 1217 |
| LMArena Creative Writing | — | 1182 |
| Short-Story Creative Writing | — | 62.6% |
| EQ-Bench Creative Writing | 1255 | — |
| LMArena Multi-Turn | — | 1206 |
| LiveBench Language | — | 25.6% |
Frequently asked questions
Is Mistral Small 3.2 better than Phi-4?
Mistral Small 3.2 and Phi-4 score almost the same on the Noometry Index (31.2 vs 31.2), so choose on price, context window or the category you care about most.
Which is cheaper, Mistral Small 3.2 or Phi-4?
Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; Mistral Small 3.2 lists at $0.0938 and $0.25.
Which has the bigger context window?
Mistral Small 3.2 does, with 256K tokens against 128K.
How many benchmarks do Mistral Small 3.2 and Phi-4 share?
4 benchmarks have published results for both models. Mistral Small 3.2 has 6 scored results on Noometry and Phi-4 has 37.