Model comparison
Mistral Large vs Phi 3 Mini 4k Instruct
Mistral Large is the stronger model overall, scoring 31.9 to 27.9 on the Noometry Index.
Last verified . 27 shared benchmarks.
Mistral AI
MicrosoftSummary
- They share 27 benchmarks with published results for both. Mistral Large 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 instruction following, where Mistral Large leads 67.9 to 47.7.
- The biggest single-benchmark swing is LiveBench Coding: 47.1% for Mistral Large and 15.5% for Phi 3 Mini 4k Instruct.
Side by side
| Mistral Large | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 31.9 | 27.9 |
| Released | 2024-02-26 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 16K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $6 | — |
| Results tracked | 51 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large leads
Mistral Large: 34.3 (#240), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | Mistral Large | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Coding | 47.1% | 15.5% |
| LMArena Coding | 1277 | 1093 |
| HumanEval+ | 62.2% | 59.1% |
| MBPP+ | 59.5% | 54.2% |
| SciCode | 36.2% | — |
| BigCodeBench Instruct | 30% | — |
| BigCodeBench Complete | 38.3% | — |
| ALE-Bench | 264.7 | — |
Agentic & Tool Use Not comparable
Mistral Large: 28.6 (#89), Phi 3 Mini 4k Instruct: —
| Benchmark | Mistral Large | Phi 3 Mini 4k Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 38.4% | — |
Reasoning Mistral Large leads
Mistral Large: 15.8 (#310), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | Mistral Large | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Reasoning | 43.5% | 26.8% |
| LMArena Hard Prompts | 1257 | 1072 |
| LiveBench Data Analysis | 50.1% | 34.7% |
| LiveBench | 48.4% | 22.4% |
| SimpleBench | 22.5% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 0% |
| DTBench | 65.1% | — |
| LMCA | 16.7% | — |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 128.52 | — |
| ForecastBench | 57.1 | — |
| HellaSwag | — | 76.7% |
| WinoGrande | — | 70.8% |
Math Phi 3 Mini 4k Instruct leads
Mistral Large: 18.2 (#291), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | Mistral Large | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Math | 42.5% | 15.7% |
| LMArena Math | 1262 | 1111 |
| OTIS Mock AIME 2024-2025 | 8.5% | — |
| Omni-MATH | 28.1% | — |
| MATH Level 5 | 50.3% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Mistral Large leads
Mistral Large: 30.1 (#230), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | Mistral Large | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1232 | 1045 |
| MMLU | 80% | 68.8% |
| GPQA Diamond | 51.3% | — |
| MMLU-Pro | 59.9% | — |
| Confabulations | 21.4% | — |
| Vectara Hallucination Rate | 4.5% | — |
| GPQA (HELM) | 43.5% | — |
| ARC (AI2) Challenge | — | 84.9% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multilingual Mistral Large leads
Mistral Large: 40.0 (#219), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | Mistral Large | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1237 | 1021 |
| LMArena Chinese | 1240 | 1021 |
| LMArena French | 1325 | 1076 |
| LMArena German | 1254 | 1044 |
| LMArena Japanese | 1188 | 935 |
| LMArena Korean | 1202 | 905 |
| LMArena Russian | 1257 | 1022 |
| LMArena Spanish | 1268 | 1085 |
Instruction Following Mistral Large leads
Mistral Large: 67.9 (#191), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | Mistral Large | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Instruction Following | 67.9% | 39.1% |
| LMArena Instruction Following | 1249 | 1053 |
| IFEval | 87.7% | — |
Long Context Mistral Large leads
Mistral Large: 38.3 (#199), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | Mistral Large | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1261 | 1044 |
Writing & Preference Mistral Large leads
Mistral Large: 40.7 (#242), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | Mistral Large | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1266 | 1073 |
| LMArena Creative Writing | 1243 | 1037 |
| LMArena Multi-Turn | 1260 | 1018 |
| LiveBench Language | 39.4% | 9.2% |
| Short-Story Creative Writing | 69% | — |
| EQ-Bench Creative Writing | 985 | — |
| WildBench | 80.1% | — |
Frequently asked questions
Is Mistral Large better than Phi 3 Mini 4k Instruct?
Mistral Large is the stronger model overall, scoring 31.9 to 27.9 on the Noometry Index.
Is Mistral Large or Phi 3 Mini 4k Instruct better for coding?
Mistral Large scores higher on coding benchmarks: 34.3 versus 26.6 in the Noometry coding category.
How many benchmarks do Mistral Large and Phi 3 Mini 4k Instruct share?
27 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.