Model comparison
MiniMax-M2.1 vs phi-3-medium 14B
MiniMax-M2.1 is the stronger model overall, scoring 38.4 to 29.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
MiniMax
MicrosoftSummary
- The widest gap is in knowledge, where MiniMax-M2.1 leads 37.7 to 9.1.
Side by side
| MiniMax-M2.1 | phi-3-medium 14B | |
|---|---|---|
| Provider | MiniMax | Microsoft |
| Noometry Index | 38.4 | 29.1 |
| Released | 2025-12-23 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 22 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.1 leads
MiniMax-M2.1: 40.1 (#132), phi-3-medium 14B: 36.3 (#198)
| Benchmark | MiniMax-M2.1 | phi-3-medium 14B |
|---|---|---|
| LMArena WebDev | 1384 | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1421 | — |
| BigCodeBench Complete | — | 48.7% |
| ALE-Bench | 623.83 | — |
Agentic & Tool Use Not comparable
MiniMax-M2.1: 27.7 (#91), phi-3-medium 14B: —
| Benchmark | MiniMax-M2.1 | phi-3-medium 14B |
|---|---|---|
| Terminal-Bench | 36.6% | — |
Reasoning Not comparable
MiniMax-M2.1: 15.8 (#301), phi-3-medium 14B: —
| Benchmark | MiniMax-M2.1 | phi-3-medium 14B |
|---|---|---|
| NYT Connections (extended) | 11.2% | — |
| LMArena Hard Prompts | 1410 | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| Epoch Capabilities Index | — | 121.18 |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math MiniMax-M2.1 leads
MiniMax-M2.1: 35.6 (#142), phi-3-medium 14B: 25.2 (#249)
| Benchmark | MiniMax-M2.1 | phi-3-medium 14B |
|---|---|---|
| LMArena Math | 1396 | — |
| MATH Level 5 | — | 17.6% |
Knowledge MiniMax-M2.1 leads
MiniMax-M2.1: 37.7 (#143), phi-3-medium 14B: 9.1 (#301)
| Benchmark | MiniMax-M2.1 | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | — | 27.6% |
| Vectara Hallucination Rate | 11.8% | — |
| LMArena Expert | 1432 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multilingual Not comparable
MiniMax-M2.1: 50.2 (#123), phi-3-medium 14B: —
| Benchmark | MiniMax-M2.1 | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1378 | — |
| LMArena Chinese | 1430 | — |
| LMArena French | 1405 | — |
| LMArena German | 1380 | — |
| LMArena Japanese | 1287 | — |
| LMArena Korean | 1297 | — |
| LMArena Russian | 1386 | — |
| LMArena Spanish | 1396 | — |
Instruction Following Not comparable
MiniMax-M2.1: 74.0 (#108), phi-3-medium 14B: —
| Benchmark | MiniMax-M2.1 | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1399 | — |
Long Context Not comparable
MiniMax-M2.1: 43.2 (#98), phi-3-medium 14B: —
| Benchmark | MiniMax-M2.1 | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1416 | — |
Writing & Preference Not comparable
MiniMax-M2.1: 58.5 (#114), phi-3-medium 14B: —
| Benchmark | MiniMax-M2.1 | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1392 | — |
| LMArena Creative Writing | 1362 | — |
| LMArena Multi-Turn | 1396 | — |
Frequently asked questions
Is MiniMax-M2.1 better than phi-3-medium 14B?
MiniMax-M2.1 is the stronger model overall, scoring 38.4 to 29.1 on the Noometry Index.
Is MiniMax-M2.1 or phi-3-medium 14B better for coding?
MiniMax-M2.1 scores higher on coding benchmarks: 40.1 versus 36.3 in the Noometry coding category.
How many benchmarks do MiniMax-M2.1 and phi-3-medium 14B share?
0 benchmarks have published results for both models. MiniMax-M2.1 has 22 scored results on Noometry and phi-3-medium 14B has 13.