Model comparison
Mistral Medium vs Phi 3 Mini 4k Instruct
Mistral Medium is the stronger model overall, scoring 36.3 to 27.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AI
MicrosoftSummary
- They share 17 benchmarks with published results for both. Mistral Medium scores higher in 7 categories and Phi 3 Mini 4k Instruct in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium leads 60.0 to 27.6.
Side by side
| Mistral Medium | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 36.3 | 27.9 |
| 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 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Medium leads
Mistral Medium: 34.2 (#243), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | Mistral Medium | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1434 | 1093 |
| FrontierCode | 8% | — |
| SciCode | 40.2% | — |
| WeirdML | 43.7% | — |
| LiveBench Coding | — | 15.5% |
| ALE-Bench | 763.98 | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Agentic & Tool Use Not comparable
Mistral Medium: 28.3 (#90), Phi 3 Mini 4k Instruct: —
| Benchmark | Mistral Medium | Phi 3 Mini 4k Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.7% | — |
Reasoning Mistral Medium leads
Mistral Medium: 24.0 (#167), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | Mistral Medium | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1072 |
| Kagi LLM Benchmark | 50% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 26.8% |
| DTBench | 75.5% | — |
| LiveBench Data Analysis | — | 34.7% |
| LMCA | 26.1% | — |
| Surface Evolver Bench | 26.9% | — |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math Mistral Medium leads
Mistral Medium: 28.1 (#245), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | Mistral Medium | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1408 | 1111 |
| OTIS Mock AIME 2024-2025 | 32.2% | — |
| ProofBench | 9% | — |
| LiveBench Math | — | 15.7% |
| MATH Level 5 | 81.6% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Phi 3 Mini 4k Instruct leads
Mistral Medium: 25.0 (#265), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | Mistral Medium | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1408 | 1045 |
| GPQA Diamond | 59.5% | — |
| Humanity's Last Exam | 4.5% | — |
| Vectara Hallucination Rate | 22.7% | — |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multimodal Not comparable
Mistral Medium: 35.3 (#88), Phi 3 Mini 4k Instruct: —
| Benchmark | Mistral Medium | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Vision | 1172 | — |
Multilingual Mistral Medium leads
Mistral Medium: 52.1 (#91), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | Mistral Medium | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1408 | 1021 |
| LMArena Chinese | 1447 | 1021 |
| LMArena French | 1459 | 1076 |
| LMArena German | 1432 | 1044 |
| LMArena Japanese | 1378 | 935 |
| LMArena Korean | 1380 | 905 |
| LMArena Russian | 1411 | 1022 |
| LMArena Spanish | 1433 | 1085 |
Instruction Following Mistral Medium leads
Mistral Medium: 73.7 (#116), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | Mistral Medium | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1398 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
Long Context Mistral Medium leads
Mistral Medium: 42.9 (#114), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | Mistral Medium | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1406 | 1044 |
Writing & Preference Mistral Medium leads
Mistral Medium: 60.0 (#103), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | Mistral Medium | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1424 | 1073 |
| LMArena Creative Writing | 1391 | 1037 |
| LMArena Multi-Turn | 1418 | 1018 |
| Short-Story Creative Writing | 77.3% | — |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is Mistral Medium better than Phi 3 Mini 4k Instruct?
Mistral Medium is the stronger model overall, scoring 36.3 to 27.9 on the Noometry Index.
Is Mistral Medium or Phi 3 Mini 4k Instruct better for coding?
Mistral Medium scores higher on coding benchmarks: 34.2 versus 26.6 in the Noometry coding category.
How many benchmarks do Mistral Medium and Phi 3 Mini 4k Instruct share?
17 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.