Model comparison
MiniMax M1 vs Phi 3 Mini 4k Instruct
MiniMax M1 is the stronger model overall, scoring 39.7 to 27.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
MiniMax
MicrosoftSummary
- They share 17 benchmarks with published results for both. MiniMax M1 scores higher in 8 categories and Phi 3 Mini 4k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax M1 leads 53.3 to 27.7.
Side by side
| MiniMax M1 | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | MiniMax | Microsoft |
| Noometry Index | 39.7 | 27.4 |
| Released | 2025-06-13 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 40K | — |
| Input $ / M tokens | $0.40 | — |
| Output $ / M tokens | $2.20 | — |
| Results tracked | 18 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax M1 leads
MiniMax M1: 39.2 (#149), Phi 3 Mini 4k Instruct: 26.1 (#319)
| Benchmark | MiniMax M1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1359 | 1093 |
| LiveBench Coding | — | 15.5% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Reasoning MiniMax M1 leads
MiniMax M1: 25.8 (#125), Phi 3 Mini 4k Instruct: 13.6 (#326)
| Benchmark | MiniMax M1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1340 | 1072 |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 26.8% |
| LiveBench Data Analysis | — | 34.7% |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math MiniMax M1 leads
MiniMax M1: 34.8 (#152), Phi 3 Mini 4k Instruct: 24.5 (#258)
| Benchmark | MiniMax M1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1360 | 1111 |
| LiveBench Math | — | 15.7% |
Knowledge MiniMax M1 leads
MiniMax M1: 35.7 (#168), Phi 3 Mini 4k Instruct: 27.9 (#241)
| Benchmark | MiniMax M1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1316 | 1045 |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multilingual MiniMax M1 leads
MiniMax M1: 46.0 (#157), Phi 3 Mini 4k Instruct: 26.5 (#275)
| Benchmark | MiniMax M1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1320 | 1021 |
| LMArena Chinese | 1361 | 1021 |
| LMArena French | 1369 | 1075 |
| LMArena German | 1350 | 1044 |
| LMArena Japanese | 1220 | 935 |
| LMArena Korean | 1263 | 905 |
| LMArena Russian | 1330 | 1022 |
| LMArena Spanish | 1354 | 1084 |
Instruction Following MiniMax M1 leads
MiniMax M1: 69.5 (#169), Phi 3 Mini 4k Instruct: 48.0 (#298)
| Benchmark | MiniMax M1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1312 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
Long Context MiniMax M1 leads
MiniMax M1: 41.4 (#136), Phi 3 Mini 4k Instruct: 31.7 (#271)
| Benchmark | MiniMax M1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1326 | 1044 |
| Fiction.LiveBench | 69.4% | — |
Writing & Preference MiniMax M1 leads
MiniMax M1: 53.3 (#155), Phi 3 Mini 4k Instruct: 27.7 (#295)
| Benchmark | MiniMax M1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1343 | 1073 |
| LMArena Creative Writing | 1298 | 1037 |
| LMArena Multi-Turn | 1335 | 1018 |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is MiniMax M1 better than Phi 3 Mini 4k Instruct?
MiniMax M1 is the stronger model overall, scoring 39.7 to 27.4 on the Noometry Index.
Is MiniMax M1 or Phi 3 Mini 4k Instruct better for coding?
MiniMax M1 scores higher on coding benchmarks: 39.2 versus 26.1 in the Noometry coding category.
How many benchmarks do MiniMax M1 and Phi 3 Mini 4k Instruct share?
17 benchmarks have published results for both models. MiniMax M1 has 18 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.