Model comparison
Mistral Small 3 vs phi-3-medium 14B
Mistral Small 3 is the stronger model overall, scoring 31.2 to 29.7 on the Noometry Index.
Last verified . 4 shared benchmarks.
Mistral AI
MicrosoftSummary
- They share 4 benchmarks with published results for both. Mistral Small 3 scores higher in 1 category and phi-3-medium 14B in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Small 3 leads 25.1 to 9.1.
- The biggest single-benchmark swing is GPQA Diamond: 47.3% for Mistral Small 3 and 27.6% for phi-3-medium 14B.
Side by side
| Mistral Small 3 | phi-3-medium 14B | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 31.2 | 29.7 |
| Released | 2025-01-30 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 33K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 24 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Mistral Small 3: 36.5 (#207), phi-3-medium 14B: 36.8 (#201)
| Benchmark | Mistral Small 3 | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | 45.3% | 37.6% |
| BigCodeBench Complete | 50.4% | 48.7% |
| LMArena Coding | 1246 | — |
Reasoning Not comparable
Mistral Small 3: 18.9 (#273), phi-3-medium 14B: —
| Benchmark | Mistral Small 3 | phi-3-medium 14B |
|---|---|---|
| Epoch Capabilities Index | 127.07 | 121.23 |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1233 | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math phi-3-medium 14B leads
Mistral Small 3: 16.3 (#295), phi-3-medium 14B: 27.3 (#250)
| Benchmark | Mistral Small 3 | phi-3-medium 14B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.7% | — |
| LMArena Math | 1240 | — |
| MATH Level 5 | — | 17.6% |
Knowledge Mistral Small 3 leads
Mistral Small 3: 25.1 (#263), phi-3-medium 14B: 9.1 (#306)
| Benchmark | Mistral Small 3 | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | 47.3% | 27.6% |
| Confabulations | 25.2% | — |
| LMArena Expert | 1202 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multilingual Not comparable
Mistral Small 3: 37.3 (#236), phi-3-medium 14B: —
| Benchmark | Mistral Small 3 | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1198 | — |
| LMArena Chinese | 1204 | — |
| LMArena French | 1203 | — |
| LMArena German | 1211 | — |
| LMArena Japanese | 1111 | — |
| LMArena Korean | 1188 | — |
| LMArena Russian | 1216 | — |
Instruction Following Not comparable
Mistral Small 3: 63.7 (#229), phi-3-medium 14B: —
| Benchmark | Mistral Small 3 | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1214 | — |
Long Context Not comparable
Mistral Small 3: 37.8 (#211), phi-3-medium 14B: —
| Benchmark | Mistral Small 3 | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1246 | — |
Writing & Preference Not comparable
Mistral Small 3: 32.2 (#280), phi-3-medium 14B: —
| Benchmark | Mistral Small 3 | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1234 | — |
| LMArena Creative Writing | 1195 | — |
| EQ-Bench Creative Writing | 707 | — |
| LMArena Multi-Turn | 1217 | — |
Frequently asked questions
Is Mistral Small 3 better than phi-3-medium 14B?
Mistral Small 3 is the stronger model overall, scoring 31.2 to 29.7 on the Noometry Index.
Is Mistral Small 3 or phi-3-medium 14B better for coding?
They score almost the same on coding (36.5 vs 36.8); test both on your own repository before choosing.
How many benchmarks do Mistral Small 3 and phi-3-medium 14B share?
4 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and phi-3-medium 14B has 13.