Model comparison
MiniMax-M2 vs Phi 3 Mini 128k Instruct
MiniMax-M2 is the stronger model overall, scoring 37.4 to 29.7 on the Noometry Index.
Last verified . 15 shared benchmarks.
MiniMax
MicrosoftSummary
- They share 15 benchmarks with published results for both. MiniMax-M2 scores higher in 7 categories and Phi 3 Mini 128k Instruct in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2 leads 53.0 to 27.1.
Side by side
| MiniMax-M2 | Phi 3 Mini 128k Instruct | |
|---|---|---|
| Provider | MiniMax | Microsoft |
| Noometry Index | 37.4 | 29.7 |
| Released | 2025-10-27 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 21 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2 leads
MiniMax-M2: 39.3 (#159), Phi 3 Mini 128k Instruct: 28.8 (#312)
| Benchmark | MiniMax-M2 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Coding | 1370 | 1039 |
| SWE-bench Verified (bash only) | 61% | — |
| LMArena WebDev | 1297 | — |
| BigCodeBench Instruct | — | 29.6% |
| BigCodeBench Complete | — | 40.6% |
Agentic & Tool Use Not comparable
MiniMax-M2: 25.1 (#109), Phi 3 Mini 128k Instruct: —
| Benchmark | MiniMax-M2 | Phi 3 Mini 128k Instruct |
|---|---|---|
| Terminal-Bench | 30% | — |
| Vending-Bench 2 | 160.6 | — |
Reasoning Too close to call
MiniMax-M2: 19.4 (#258), Phi 3 Mini 128k Instruct: 19.6 (#256)
| Benchmark | MiniMax-M2 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1357 | 1028 |
| Kagi LLM Benchmark | 57.8% | — |
| NYT Connections (extended) | 14.8% | — |
Math MiniMax-M2 leads
MiniMax-M2: 37.3 (#160), Phi 3 Mini 128k Instruct: 31.6 (#222)
| Benchmark | MiniMax-M2 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Math | 1352 | 1089 |
Knowledge MiniMax-M2 leads
MiniMax-M2: 37.0 (#163), Phi 3 Mini 128k Instruct: 26.8 (#254)
| Benchmark | MiniMax-M2 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Expert | 1337 | 984 |
Multilingual MiniMax-M2 leads
MiniMax-M2: 45.3 (#171), Phi 3 Mini 128k Instruct: 25.2 (#285)
| Benchmark | MiniMax-M2 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Non-English | 1313 | 1000 |
| LMArena Chinese | 1366 | 1016 |
| LMArena French | 1335 | 1039 |
| LMArena German | 1355 | 1006 |
| LMArena Russian | 1331 | 1004 |
| LMArena Spanish | 1326 | 1059 |
| LMArena Japanese | — | 899 |
| LMArena Korean | — | 856 |
Instruction Following MiniMax-M2 leads
MiniMax-M2: 70.2 (#166), Phi 3 Mini 128k Instruct: 51.8 (#294)
| Benchmark | MiniMax-M2 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Instruction Following | 1328 | 1023 |
Long Context MiniMax-M2 leads
MiniMax-M2: 40.5 (#153), Phi 3 Mini 128k Instruct: 30.4 (#289)
| Benchmark | MiniMax-M2 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Longer Query | 1331 | 996 |
Writing & Preference MiniMax-M2 leads
MiniMax-M2: 53.0 (#162), Phi 3 Mini 128k Instruct: 27.1 (#301)
| Benchmark | MiniMax-M2 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Text | 1340 | 1050 |
| LMArena Creative Writing | 1286 | 1024 |
| LMArena Multi-Turn | 1361 | 989 |
Frequently asked questions
Is MiniMax-M2 better than Phi 3 Mini 128k Instruct?
MiniMax-M2 is the stronger model overall, scoring 37.4 to 29.7 on the Noometry Index.
Is MiniMax-M2 or Phi 3 Mini 128k Instruct better for coding?
MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 28.8 in the Noometry coding category.
How many benchmarks do MiniMax-M2 and Phi 3 Mini 128k Instruct share?
15 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.