Model comparison
Mistral Small vs Phi-4
Mistral Small is the stronger model overall, scoring 33.4 to 31.2 on the Noometry Index. Phi-4 costs 3.0× less per token, which makes it the better buy when Mistral Small's lead doesn't matter for your workload.
Last verified . 32 shared benchmarks.
Mistral AI
MicrosoftSummary
- They share 32 benchmarks with published results for both. Mistral Small scores higher in 6 categories and Phi-4 in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Small leads 52.5 to 40.5.
- The biggest single-benchmark swing is MATH Level 5: 46.8% for Mistral Small and 64.9% for Phi-4.
- Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $0.15 / $0.60 for Mistral Small.
- Mistral Small accepts more context: 262K tokens versus 128K.
Side by side
| Mistral Small | Phi-4 | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 33.4 | 31.2 |
| Released | 2024-02-26 | 2024-12-11 |
| Weights | Open | Open |
| Context window | 262K | 128K |
| Max output | 256K | 4K |
| Input $ / M tokens | $0.15 | $0.07 |
| Output $ / M tokens | $0.60 | $0.14 |
| Results tracked | 39 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Mistral Small: 34.0 (#247), Phi-4: 34.4 (#239)
| Benchmark | Mistral Small | Phi-4 |
|---|---|---|
| BigCodeBench Instruct | 36.1% | 45.5% |
| LiveBench Coding | 36.2% | 30.7% |
| LMArena Coding | 1362 | 1231 |
| BigCodeBench Complete | 46.6% | 55.4% |
| SciCode | 26.5% | — |
| ALE-Bench | 497.62 | — |
Agentic & Tool Use Mistral Small leads
Mistral Small: 28.1 (#93), Phi-4: 22.8 (#128)
| Benchmark | Mistral Small | Phi-4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.1% | 28.8% |
| BALROG | — | 11.6% |
Reasoning Mistral Small leads
Mistral Small: 19.8 (#250), Phi-4: 17.7 (#291)
| Benchmark | Mistral Small | Phi-4 |
|---|---|---|
| LiveBench Reasoning | 44.8% | 47.8% |
| LMArena Hard Prompts | 1335 | 1220 |
| LiveBench Data Analysis | 53.7% | 45.2% |
| LiveBench | 44% | 41.6% |
| Kagi LLM Benchmark | 37.8% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 1% |
| DTBench | 70.9% | — |
| LMCA | 20.6% | — |
| Epoch Capabilities Index | — | 130.42 |
Math Phi-4 leads
Mistral Small: 16.4 (#293), Phi-4: 20.8 (#285)
| Benchmark | Mistral Small | Phi-4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 5.8% | 13.8% |
| LiveBench Math | 39.9% | 42% |
| LMArena Math | 1341 | 1246 |
| MATH Level 5 | 46.8% | 64.9% |
Knowledge Phi-4 leads
Mistral Small: 31.0 (#222), Phi-4: 32.6 (#209)
| Benchmark | Mistral Small | Phi-4 |
|---|---|---|
| GPQA Diamond | 47.5% | 56.1% |
| Vectara Hallucination Rate | 5.1% | 3.7% |
| LMArena Expert | 1291 | 1203 |
| MMLU | 68.7% | 84.8% |
| Confabulations | — | 29.4% |
Multimodal Not comparable
Mistral Small: 33.5 (#96), Phi-4: —
| Benchmark | Mistral Small | Phi-4 |
|---|---|---|
| LMArena Vision | 1142 | — |
Multilingual Mistral Small leads
Mistral Small: 45.5 (#169), Phi-4: 37.2 (#237)
| Benchmark | Mistral Small | Phi-4 |
|---|---|---|
| LMArena Non-English | 1315 | 1197 |
| LMArena Chinese | 1340 | 1212 |
| LMArena French | 1337 | 1224 |
| LMArena German | 1340 | 1222 |
| LMArena Japanese | 1275 | 1158 |
| LMArena Korean | 1259 | 1151 |
| LMArena Russian | 1324 | 1209 |
| LMArena Spanish | 1346 | 1234 |
Instruction Following Mistral Small leads
Mistral Small: 66.4 (#209), Phi-4: 60.4 (#251)
| Benchmark | Mistral Small | Phi-4 |
|---|---|---|
| LiveBench Instruction Following | 63.7% | 58.4% |
| LMArena Instruction Following | 1310 | 1201 |
Long Context Mistral Small leads
Mistral Small: 40.4 (#156), Phi-4: 36.9 (#226)
| Benchmark | Mistral Small | Phi-4 |
|---|---|---|
| LMArena Longer Query | 1327 | 1217 |
Writing & Preference Mistral Small leads
Mistral Small: 52.5 (#171), Phi-4: 40.5 (#244)
| Benchmark | Mistral Small | Phi-4 |
|---|---|---|
| LMArena Text | 1338 | 1217 |
| LMArena Creative Writing | 1305 | 1182 |
| LMArena Multi-Turn | 1344 | 1206 |
| LiveBench Language | 30.5% | 25.6% |
| Short-Story Creative Writing | — | 62.6% |
Frequently asked questions
Is Mistral Small better than Phi-4?
Mistral Small is the stronger model overall, scoring 33.4 to 31.2 on the Noometry Index. Phi-4 costs 3.0× less per token, which makes it the better buy when Mistral Small's lead doesn't matter for your workload.
Which is cheaper, Mistral Small 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 lists at $0.15 and $0.60.
Is Mistral Small or Phi-4 better for coding?
They score almost the same on coding (34.0 vs 34.4); test both on your own repository before choosing.
Which has the bigger context window?
Mistral Small does, with 262K tokens against 128K.
How many benchmarks do Mistral Small and Phi-4 share?
32 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and Phi-4 has 37.