Model comparison
Mistral Medium vs phi-3-medium 14B
Mistral Medium is the stronger model overall, scoring 36.3 to 29.7 on the Noometry Index.
Last verified . 2 shared benchmarks.
Mistral AI
MicrosoftSummary
- They share 2 benchmarks with published results for both. Mistral Medium scores higher in 2 categories and phi-3-medium 14B in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Medium leads 25.0 to 9.1.
- The biggest single-benchmark swing is MATH Level 5: 81.6% for Mistral Medium and 17.6% for phi-3-medium 14B.
Side by side
| Mistral Medium | phi-3-medium 14B | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 36.3 | 29.7 |
| Released | 2023-12-11 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 262K | — |
| Input $ / M tokens | $1.50 | — |
| Output $ / M tokens | $7.50 | — |
| Results tracked | 36 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding phi-3-medium 14B leads
Mistral Medium: 34.2 (#243), phi-3-medium 14B: 36.8 (#201)
| Benchmark | Mistral Medium | phi-3-medium 14B |
|---|---|---|
| FrontierCode | 8% | — |
| SciCode | 40.2% | — |
| WeirdML | 43.7% | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1434 | — |
| BigCodeBench Complete | — | 48.7% |
| ALE-Bench | 763.98 | — |
Agentic & Tool Use Not comparable
Mistral Medium: 28.3 (#90), phi-3-medium 14B: —
| Benchmark | Mistral Medium | phi-3-medium 14B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.7% | — |
Reasoning Not comparable
Mistral Medium: 24.0 (#167), phi-3-medium 14B: —
| Benchmark | Mistral Medium | phi-3-medium 14B |
|---|---|---|
| Kagi LLM Benchmark | 50% | — |
| CritPt | 0% | — |
| LMArena Hard Prompts | 1426 | — |
| DTBench | 75.5% | — |
| LMCA | 26.1% | — |
| Surface Evolver Bench | 26.9% | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| Epoch Capabilities Index | — | 121.23 |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math Too close to call
Mistral Medium: 28.1 (#245), phi-3-medium 14B: 27.3 (#250)
| Benchmark | Mistral Medium | phi-3-medium 14B |
|---|---|---|
| MATH Level 5 | 81.6% | 17.6% |
| OTIS Mock AIME 2024-2025 | 32.2% | — |
| ProofBench | 9% | — |
| LMArena Math | 1408 | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Mistral Medium leads
Mistral Medium: 25.0 (#265), phi-3-medium 14B: 9.1 (#306)
| Benchmark | Mistral Medium | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | 59.5% | 27.6% |
| Humanity's Last Exam | 4.5% | — |
| Vectara Hallucination Rate | 22.7% | — |
| LMArena Expert | 1408 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multimodal Not comparable
Mistral Medium: 35.3 (#88), phi-3-medium 14B: —
| Benchmark | Mistral Medium | phi-3-medium 14B |
|---|---|---|
| LMArena Vision | 1172 | — |
Multilingual Not comparable
Mistral Medium: 52.1 (#91), phi-3-medium 14B: —
| Benchmark | Mistral Medium | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1408 | — |
| LMArena Chinese | 1447 | — |
| LMArena French | 1459 | — |
| LMArena German | 1432 | — |
| LMArena Japanese | 1378 | — |
| LMArena Korean | 1380 | — |
| LMArena Russian | 1411 | — |
| LMArena Spanish | 1433 | — |
Instruction Following Not comparable
Mistral Medium: 73.7 (#116), phi-3-medium 14B: —
| Benchmark | Mistral Medium | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1398 | — |
Long Context Not comparable
Mistral Medium: 42.9 (#114), phi-3-medium 14B: —
| Benchmark | Mistral Medium | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1406 | — |
Writing & Preference Not comparable
Mistral Medium: 60.0 (#103), phi-3-medium 14B: —
| Benchmark | Mistral Medium | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1424 | — |
| LMArena Creative Writing | 1391 | — |
| Short-Story Creative Writing | 77.3% | — |
| LMArena Multi-Turn | 1418 | — |
Frequently asked questions
Is Mistral Medium better than phi-3-medium 14B?
Mistral Medium is the stronger model overall, scoring 36.3 to 29.7 on the Noometry Index.
Is Mistral Medium or phi-3-medium 14B better for coding?
phi-3-medium 14B scores higher on coding benchmarks: 36.8 versus 34.2 in the Noometry coding category.
How many benchmarks do Mistral Medium and phi-3-medium 14B share?
2 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and phi-3-medium 14B has 13.