Model comparison
Mistral Small vs phi-3-medium 14B
Mistral Small is the stronger model overall, scoring 33.4 to 29.7 on the Noometry Index.
Last verified . 5 shared benchmarks.
Mistral AI
MicrosoftSummary
- They share 5 benchmarks with published results for both. Mistral Small scores higher in 1 category and phi-3-medium 14B in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Small leads 31.0 to 9.1.
- The biggest single-benchmark swing is MATH Level 5: 46.8% for Mistral Small and 17.6% for phi-3-medium 14B.
Side by side
| Mistral Small | phi-3-medium 14B | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 33.4 | 29.7 |
| Released | 2024-02-26 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 256K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 39 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding phi-3-medium 14B leads
Mistral Small: 34.0 (#247), phi-3-medium 14B: 36.8 (#201)
| Benchmark | Mistral Small | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | 36.1% | 37.6% |
| BigCodeBench Complete | 46.6% | 48.7% |
| SciCode | 26.5% | — |
| LiveBench Coding | 36.2% | — |
| LMArena Coding | 1362 | — |
| ALE-Bench | 497.62 | — |
Agentic & Tool Use Not comparable
Mistral Small: 28.1 (#93), phi-3-medium 14B: —
| Benchmark | Mistral Small | phi-3-medium 14B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.1% | — |
Reasoning Not comparable
Mistral Small: 19.8 (#250), phi-3-medium 14B: —
| Benchmark | Mistral Small | phi-3-medium 14B |
|---|---|---|
| Kagi LLM Benchmark | 37.8% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | 44.8% | — |
| LMArena Hard Prompts | 1335 | — |
| DTBench | 70.9% | — |
| LiveBench Data Analysis | 53.7% | — |
| LMCA | 20.6% | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| Epoch Capabilities Index | — | 121.23 |
| HellaSwag | — | 82.4% |
| LiveBench | 44% | — |
| WinoGrande | — | 81.5% |
Math phi-3-medium 14B leads
Mistral Small: 16.4 (#293), phi-3-medium 14B: 27.3 (#250)
| Benchmark | Mistral Small | phi-3-medium 14B |
|---|---|---|
| MATH Level 5 | 46.8% | 17.6% |
| OTIS Mock AIME 2024-2025 | 5.8% | — |
| LiveBench Math | 39.9% | — |
| LMArena Math | 1341 | — |
Knowledge Mistral Small leads
Mistral Small: 31.0 (#222), phi-3-medium 14B: 9.1 (#306)
| Benchmark | Mistral Small | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | 47.5% | 27.6% |
| MMLU | 68.7% | 78% |
| Vectara Hallucination Rate | 5.1% | — |
| LMArena Expert | 1291 | — |
| ARC (AI2) Challenge | — | 91.6% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multimodal Not comparable
Mistral Small: 33.5 (#96), phi-3-medium 14B: —
| Benchmark | Mistral Small | phi-3-medium 14B |
|---|---|---|
| LMArena Vision | 1142 | — |
Multilingual Not comparable
Mistral Small: 45.5 (#169), phi-3-medium 14B: —
| Benchmark | Mistral Small | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1315 | — |
| LMArena Chinese | 1340 | — |
| LMArena French | 1337 | — |
| LMArena German | 1340 | — |
| LMArena Japanese | 1275 | — |
| LMArena Korean | 1259 | — |
| LMArena Russian | 1324 | — |
| LMArena Spanish | 1346 | — |
Instruction Following Not comparable
Mistral Small: 66.4 (#209), phi-3-medium 14B: —
| Benchmark | Mistral Small | phi-3-medium 14B |
|---|---|---|
| LiveBench Instruction Following | 63.7% | — |
| LMArena Instruction Following | 1310 | — |
Long Context Not comparable
Mistral Small: 40.4 (#156), phi-3-medium 14B: —
| Benchmark | Mistral Small | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1327 | — |
Writing & Preference Not comparable
Mistral Small: 52.5 (#171), phi-3-medium 14B: —
| Benchmark | Mistral Small | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1338 | — |
| LMArena Creative Writing | 1305 | — |
| LMArena Multi-Turn | 1344 | — |
| LiveBench Language | 30.5% | — |
Frequently asked questions
Is Mistral Small better than phi-3-medium 14B?
Mistral Small is the stronger model overall, scoring 33.4 to 29.7 on the Noometry Index.
Is Mistral Small or phi-3-medium 14B better for coding?
phi-3-medium 14B scores higher on coding benchmarks: 36.8 versus 34.0 in the Noometry coding category.
How many benchmarks do Mistral Small and phi-3-medium 14B share?
5 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and phi-3-medium 14B has 13.