Model comparison
MiniMax-M3 vs Phi-4 Mini
MiniMax-M3 is the stronger model overall, scoring 43.8 to 30.9 on the Noometry Index. Phi-4 Mini costs 4.0× less per token, which makes it the better buy when MiniMax-M3's lead doesn't matter for your workload.
Last verified . 2 shared benchmarks.
MiniMax
MicrosoftSummary
- They share 2 benchmarks with published results for both. MiniMax-M3 scores higher in 3 categories and Phi-4 Mini in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 25.3.
- The biggest single-benchmark swing is SciCode: 47.1% for MiniMax-M3 and 10.8% for Phi-4 Mini.
- Phi-4 Mini is cheaper at $0.075 / $0.30 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M3.
- MiniMax-M3 accepts more context: 1M tokens versus 128K.
Side by side
| MiniMax-M3 | Phi-4 Mini | |
|---|---|---|
| Provider | MiniMax | Microsoft |
| Noometry Index | 43.8 | 30.9 |
| Released | 2026-06-01 | 2024-12-11 |
| Weights | Open | Open |
| Context window | 1M | 128K |
| Max output | 512K | 4K |
| Input $ / M tokens | $0.30 | $0.075 |
| Output $ / M tokens | $1.20 | $0.30 |
| Results tracked | 41 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M3 leads
MiniMax-M3: 41.8 (#118), Phi-4 Mini: 28.1 (#317)
| Benchmark | MiniMax-M3 | Phi-4 Mini |
|---|---|---|
| SciCode | 47.1% | 10.8% |
| FrontierCode | 14.7% | — |
| LMArena WebDev | 1482 | — |
| LMArena Coding | 1469 | — |
| ALE-Bench | 640.02 | — |
Agentic & Tool Use Not comparable
MiniMax-M3: 22.6 (#130), Phi-4 Mini: —
| Benchmark | MiniMax-M3 | Phi-4 Mini |
|---|---|---|
| APEX-Agents | 37.7% | — |
| OSWorld 2.0 | 4.6% | — |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 2,158 | — |
Reasoning MiniMax-M3 leads
MiniMax-M3: 30.1 (#87), Phi-4 Mini: 22.4 (#195)
| Benchmark | MiniMax-M3 | Phi-4 Mini |
|---|---|---|
| CritPt | 3.7% | 0% |
| SimpleBench | 45.8% | — |
| NYT Connections (extended) | 65.1% | — |
| Chess Puzzles | 14% | — |
| LMArena Hard Prompts | 1447 | — |
| Mystery Game Puzzles | 8% | — |
| DTBench | 78.9% | — |
| LMCA | 33.7% | — |
| Surface Evolver Bench | 55% | — |
| Epoch Capabilities Index | 146.95 | — |
| ForecastBench | 61.4 | — |
Math Not comparable
MiniMax-M3: 40.0 (#95), Phi-4 Mini: —
| Benchmark | MiniMax-M3 | Phi-4 Mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| ProofBench | 18% | — |
| LMArena Math | 1429 | — |
Knowledge MiniMax-M3 leads
MiniMax-M3: 58.4 (#35), Phi-4 Mini: 25.3 (#262)
| Benchmark | MiniMax-M3 | Phi-4 Mini |
|---|---|---|
| GPQA Diamond | 90.9% | — |
| Vectara Hallucination Rate | — | 23.5% |
| LMArena Expert | 1461 | — |
Multimodal Not comparable
MiniMax-M3: 40.2 (#51), Phi-4 Mini: —
| Benchmark | MiniMax-M3 | Phi-4 Mini |
|---|---|---|
| LMArena Vision | 1253 | — |
| LMArena Document | 1435 | — |
Multilingual Not comparable
MiniMax-M3: 53.0 (#75), Phi-4 Mini: —
| Benchmark | MiniMax-M3 | Phi-4 Mini |
|---|---|---|
| LMArena Non-English | 1420 | — |
| LMArena Chinese | 1463 | — |
| LMArena French | 1447 | — |
| LMArena German | 1426 | — |
| LMArena Japanese | 1381 | — |
| LMArena Korean | 1372 | — |
| LMArena Russian | 1428 | — |
| LMArena Spanish | 1432 | — |
Instruction Following Not comparable
MiniMax-M3: 75.5 (#62), Phi-4 Mini: —
| Benchmark | MiniMax-M3 | Phi-4 Mini |
|---|---|---|
| LMArena Instruction Following | 1433 | — |
Long Context Not comparable
MiniMax-M3: 44.2 (#72), Phi-4 Mini: —
| Benchmark | MiniMax-M3 | Phi-4 Mini |
|---|---|---|
| LMArena Longer Query | 1445 | — |
Writing & Preference Not comparable
MiniMax-M3: 62.1 (#83), Phi-4 Mini: —
| Benchmark | MiniMax-M3 | Phi-4 Mini |
|---|---|---|
| LMArena Text | 1433 | — |
| LMArena Creative Writing | 1404 | — |
| EQ-Bench 4 | 1150 | — |
| LMArena Multi-Turn | 1442 | — |
Frequently asked questions
Is MiniMax-M3 better than Phi-4 Mini?
MiniMax-M3 is the stronger model overall, scoring 43.8 to 30.9 on the Noometry Index. Phi-4 Mini costs 4.0× less per token, which makes it the better buy when MiniMax-M3's lead doesn't matter for your workload.
Which is cheaper, MiniMax-M3 or Phi-4 Mini?
Phi-4 Mini is cheaper. It lists at $0.075 per million input tokens and $0.30 per million output tokens; MiniMax-M3 lists at $0.30 and $1.20.
Is MiniMax-M3 or Phi-4 Mini better for coding?
MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 28.1 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M3 does, with 1M tokens against 128K.
How many benchmarks do MiniMax-M3 and Phi-4 Mini share?
2 benchmarks have published results for both models. MiniMax-M3 has 41 scored results on Noometry and Phi-4 Mini has 3.