Model comparison
MiniMax-M3 vs phi-3-medium 14B
MiniMax-M3 is the stronger model overall, scoring 43.5 to 29.1 on the Noometry Index.
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-3-medium 14B in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 9.1.
- The biggest single-benchmark swing is GPQA Diamond: 90.9% for MiniMax-M3 and 27.6% for phi-3-medium 14B.
Side by side
| MiniMax-M3 | phi-3-medium 14B | |
|---|---|---|
| Provider | MiniMax | Microsoft |
| Noometry Index | 43.5 | 29.1 |
| Released | 2026-06-01 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 512K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 41 | 13 |
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 14B: 36.3 (#198)
| Benchmark | MiniMax-M3 | phi-3-medium 14B |
|---|---|---|
| FrontierCode | 14.7% | — |
| LMArena WebDev | 1482 | — |
| SciCode | 47.1% | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1470 | — |
| BigCodeBench Complete | — | 48.7% |
| ALE-Bench | 640.02 | — |
Agentic & Tool Use Not comparable
MiniMax-M3: 22.5 (#121), phi-3-medium 14B: —
| Benchmark | MiniMax-M3 | phi-3-medium 14B |
|---|---|---|
| APEX-Agents | 37.7% | — |
| OSWorld 2.0 | 4.6% | — |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 2,158 | — |
Reasoning Not comparable
MiniMax-M3: 29.3 (#83), phi-3-medium 14B: —
| Benchmark | MiniMax-M3 | phi-3-medium 14B |
|---|---|---|
| Epoch Capabilities Index | 147 | 121.18 |
| SimpleBench | 45.8% | — |
| NYT Connections (extended) | 65.1% | — |
| CritPt | 3.7% | — |
| Chess Puzzles | 14% | — |
| LMArena Hard Prompts | 1447 | — |
| Mystery Game Puzzles | 8% | — |
| DTBench | 78.9% | — |
| LMCA | 33.7% | — |
| Surface Evolver Bench | 55% | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| ForecastBench | 61.4 | — |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math MiniMax-M3 leads
MiniMax-M3: 39.1 (#83), phi-3-medium 14B: 25.2 (#249)
| Benchmark | MiniMax-M3 | phi-3-medium 14B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| ProofBench | 18% | — |
| LMArena Math | 1432 | — |
| MATH Level 5 | — | 17.6% |
Knowledge MiniMax-M3 leads
MiniMax-M3: 58.4 (#32), phi-3-medium 14B: 9.1 (#301)
| Benchmark | MiniMax-M3 | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | 90.9% | 27.6% |
| LMArena Expert | 1462 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multimodal Not comparable
MiniMax-M3: 39.5 (#45), phi-3-medium 14B: —
| Benchmark | MiniMax-M3 | phi-3-medium 14B |
|---|---|---|
| LMArena Vision | 1254 | — |
| LMArena Document | 1435 | — |
Multilingual Not comparable
MiniMax-M3: 53.2 (#70), phi-3-medium 14B: —
| Benchmark | MiniMax-M3 | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1420 | — |
| LMArena Chinese | 1465 | — |
| LMArena French | 1445 | — |
| LMArena German | 1424 | — |
| LMArena Japanese | 1381 | — |
| LMArena Korean | 1372 | — |
| LMArena Russian | 1430 | — |
| LMArena Spanish | 1431 | — |
Instruction Following Not comparable
MiniMax-M3: 75.7 (#56), phi-3-medium 14B: —
| Benchmark | MiniMax-M3 | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1433 | — |
Long Context Not comparable
MiniMax-M3: 44.2 (#68), phi-3-medium 14B: —
| Benchmark | MiniMax-M3 | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1445 | — |
Writing & Preference Not comparable
MiniMax-M3: 62.3 (#79), phi-3-medium 14B: —
| Benchmark | MiniMax-M3 | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1433 | — |
| LMArena Creative Writing | 1405 | — |
| EQ-Bench 4 | 1150 | — |
| LMArena Multi-Turn | 1441 | — |
Frequently asked questions
Is MiniMax-M3 better than phi-3-medium 14B?
MiniMax-M3 is the stronger model overall, scoring 43.5 to 29.1 on the Noometry Index.
Is MiniMax-M3 or phi-3-medium 14B better for coding?
MiniMax-M3 scores higher on coding benchmarks: 41.5 versus 36.3 in the Noometry coding category.
How many benchmarks do MiniMax-M3 and phi-3-medium 14B share?
2 benchmarks have published results for both models. MiniMax-M3 has 41 scored results on Noometry and phi-3-medium 14B has 13.