Model comparison
MiniMax-M3 vs Phi 3 Medium 4k Instruct
MiniMax-M3 is the stronger model overall, scoring 43.5 to 32.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
MiniMax
MicrosoftSummary
- They share 17 benchmarks with published results for both. MiniMax-M3 scores higher in 8 categories and Phi 3 Medium 4k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 29.6.
Side by side
| MiniMax-M3 | Phi 3 Medium 4k Instruct | |
|---|---|---|
| Provider | MiniMax | Microsoft |
| Noometry Index | 43.5 | 32.4 |
| Released | 2026-06-01 | — |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 512K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 41 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M3 leads
MiniMax-M3: 41.5 (#111), Phi 3 Medium 4k Instruct: 32.3 (#263)
| Benchmark | MiniMax-M3 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Coding | 1470 | 1130 |
| FrontierCode | 14.7% | — |
| LMArena WebDev | 1482 | — |
| SciCode | 47.1% | — |
| ALE-Bench | 640.02 | — |
Agentic & Tool Use Not comparable
MiniMax-M3: 22.5 (#121), Phi 3 Medium 4k Instruct: —
| Benchmark | MiniMax-M3 | Phi 3 Medium 4k Instruct |
|---|---|---|
| APEX-Agents | 37.7% | — |
| OSWorld 2.0 | 4.6% | — |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 2,158 | — |
Reasoning MiniMax-M3 leads
MiniMax-M3: 29.3 (#83), Phi 3 Medium 4k Instruct: 20.8 (#214)
| Benchmark | MiniMax-M3 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1127 |
| SimpleBench | 45.8% | — |
| NYT Connections (extended) | 65.1% | — |
| CritPt | 3.7% | — |
| Chess Puzzles | 14% | — |
| Mystery Game Puzzles | 8% | — |
| DTBench | 78.9% | — |
| LMCA | 33.7% | — |
| Surface Evolver Bench | 55% | — |
| Epoch Capabilities Index | 147 | — |
| ForecastBench | 61.4 | — |
Math MiniMax-M3 leads
MiniMax-M3: 39.1 (#83), Phi 3 Medium 4k Instruct: 30.9 (#202)
| Benchmark | MiniMax-M3 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Math | 1432 | 1173 |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| ProofBench | 18% | — |
Knowledge MiniMax-M3 leads
MiniMax-M3: 58.4 (#32), Phi 3 Medium 4k Instruct: 29.6 (#226)
| Benchmark | MiniMax-M3 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Expert | 1462 | 1108 |
| GPQA Diamond | 90.9% | — |
Multimodal Not comparable
MiniMax-M3: 39.5 (#45), Phi 3 Medium 4k Instruct: —
| Benchmark | MiniMax-M3 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Vision | 1254 | — |
| LMArena Document | 1435 | — |
Multilingual MiniMax-M3 leads
MiniMax-M3: 53.2 (#70), Phi 3 Medium 4k Instruct: 30.8 (#258)
| Benchmark | MiniMax-M3 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | 1420 | 1094 |
| LMArena Chinese | 1465 | 1108 |
| LMArena French | 1445 | 1109 |
| LMArena German | 1424 | 1101 |
| LMArena Japanese | 1381 | 1042 |
| LMArena Korean | 1372 | 954 |
| LMArena Russian | 1430 | 1145 |
| LMArena Spanish | 1431 | 1095 |
Instruction Following MiniMax-M3 leads
MiniMax-M3: 75.7 (#56), Phi 3 Medium 4k Instruct: 57.8 (#263)
| Benchmark | MiniMax-M3 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1433 | 1114 |
Long Context MiniMax-M3 leads
MiniMax-M3: 44.2 (#68), Phi 3 Medium 4k Instruct: 33.9 (#250)
| Benchmark | MiniMax-M3 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1445 | 1120 |
Writing & Preference MiniMax-M3 leads
MiniMax-M3: 62.3 (#79), Phi 3 Medium 4k Instruct: 34.3 (#267)
| Benchmark | MiniMax-M3 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | 1433 | 1138 |
| LMArena Creative Writing | 1405 | 1106 |
| LMArena Multi-Turn | 1441 | 1088 |
| EQ-Bench 4 | 1150 | — |
Frequently asked questions
Is MiniMax-M3 better than Phi 3 Medium 4k Instruct?
MiniMax-M3 is the stronger model overall, scoring 43.5 to 32.4 on the Noometry Index.
Is MiniMax-M3 or Phi 3 Medium 4k Instruct better for coding?
MiniMax-M3 scores higher on coding benchmarks: 41.5 versus 32.3 in the Noometry coding category.
How many benchmarks do MiniMax-M3 and Phi 3 Medium 4k Instruct share?
17 benchmarks have published results for both models. MiniMax-M3 has 41 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.