Model comparison
MiniMax-M2.1 vs Phi 3 Mini 128k Instruct
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 29.7 on the Noometry Index.
Last verified . 17 shared benchmarks.
MiniMax
MicrosoftSummary
- They share 17 benchmarks with published results for both. MiniMax-M2.1 scores higher in 7 categories and Phi 3 Mini 128k Instruct in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2.1 leads 58.3 to 27.1.
Side by side
| MiniMax-M2.1 | Phi 3 Mini 128k Instruct | |
|---|---|---|
| Provider | MiniMax | Microsoft |
| Noometry Index | 38.9 | 29.7 |
| 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 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.1 leads
MiniMax-M2.1: 40.4 (#143), Phi 3 Mini 128k Instruct: 28.8 (#312)
| Benchmark | MiniMax-M2.1 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Coding | 1421 | 1039 |
| LMArena WebDev | 1384 | — |
| BigCodeBench Instruct | — | 29.6% |
| BigCodeBench Complete | — | 40.6% |
| ALE-Bench | 623.83 | — |
Agentic & Tool Use Not comparable
MiniMax-M2.1: 27.9 (#98), Phi 3 Mini 128k Instruct: —
| Benchmark | MiniMax-M2.1 | Phi 3 Mini 128k Instruct |
|---|---|---|
| Terminal-Bench | 36.6% | — |
Reasoning Phi 3 Mini 128k Instruct leads
MiniMax-M2.1: 16.6 (#302), Phi 3 Mini 128k Instruct: 19.6 (#256)
| Benchmark | MiniMax-M2.1 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1411 | 1028 |
| NYT Connections (extended) | 11.2% | — |
Math MiniMax-M2.1 leads
MiniMax-M2.1: 38.3 (#138), Phi 3 Mini 128k Instruct: 31.6 (#222)
| Benchmark | MiniMax-M2.1 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Math | 1397 | 1089 |
Knowledge MiniMax-M2.1 leads
MiniMax-M2.1: 38.3 (#147), Phi 3 Mini 128k Instruct: 26.8 (#254)
| Benchmark | MiniMax-M2.1 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Expert | 1431 | 984 |
| Vectara Hallucination Rate | 11.8% | — |
Multilingual MiniMax-M2.1 leads
MiniMax-M2.1: 50.0 (#128), Phi 3 Mini 128k Instruct: 25.2 (#285)
| Benchmark | MiniMax-M2.1 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Non-English | 1378 | 1000 |
| LMArena Chinese | 1430 | 1016 |
| LMArena French | 1404 | 1039 |
| LMArena German | 1381 | 1006 |
| LMArena Japanese | 1287 | 899 |
| LMArena Korean | 1298 | 856 |
| LMArena Russian | 1387 | 1004 |
| LMArena Spanish | 1397 | 1059 |
Instruction Following MiniMax-M2.1 leads
MiniMax-M2.1: 73.8 (#112), Phi 3 Mini 128k Instruct: 51.8 (#294)
| Benchmark | MiniMax-M2.1 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Instruction Following | 1400 | 1023 |
Long Context MiniMax-M2.1 leads
MiniMax-M2.1: 43.2 (#101), Phi 3 Mini 128k Instruct: 30.4 (#289)
| Benchmark | MiniMax-M2.1 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Longer Query | 1416 | 996 |
Writing & Preference MiniMax-M2.1 leads
MiniMax-M2.1: 58.3 (#120), Phi 3 Mini 128k Instruct: 27.1 (#301)
| Benchmark | MiniMax-M2.1 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Text | 1392 | 1050 |
| LMArena Creative Writing | 1361 | 1024 |
| LMArena Multi-Turn | 1396 | 989 |
Frequently asked questions
Is MiniMax-M2.1 better than Phi 3 Mini 128k Instruct?
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 29.7 on the Noometry Index.
Is MiniMax-M2.1 or Phi 3 Mini 128k Instruct better for coding?
MiniMax-M2.1 scores higher on coding benchmarks: 40.4 versus 28.8 in the Noometry coding category.
How many benchmarks do MiniMax-M2.1 and Phi 3 Mini 128k Instruct share?
17 benchmarks have published results for both models. MiniMax-M2.1 has 22 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.