Model comparison
MiniMax-M2.5 vs Phi 3 Mini 128k Instruct
MiniMax-M2.5 is the stronger model overall, scoring 38.1 to 29.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
MiniMax
MicrosoftSummary
- They share 17 benchmarks with published results for both. MiniMax-M2.5 scores higher in 6 categories and Phi 3 Mini 128k Instruct in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2.5 leads 54.1 to 27.3.
Side by side
| MiniMax-M2.5 | Phi 3 Mini 128k Instruct | |
|---|---|---|
| Provider | MiniMax | Microsoft |
| Noometry Index | 38.1 | 29.1 |
| Released | 2026-02-12 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 33 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.5 leads
MiniMax-M2.5: 47.9 (#53), Phi 3 Mini 128k Instruct: 28.3 (#307)
| Benchmark | MiniMax-M2.5 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Coding | 1380 | 1040 |
| SWE-bench Verified (bash only) | 75.8% | — |
| LMArena WebDev | 1386 | — |
| SWE-bench Multilingual | 68.3% | — |
| BigCodeBench Instruct | — | 29.6% |
| BigCodeBench Complete | — | 40.6% |
| ALE-Bench | 618.17 | — |
Agentic & Tool Use Not comparable
MiniMax-M2.5: 30.2 (#70), Phi 3 Mini 128k Instruct: —
| Benchmark | MiniMax-M2.5 | Phi 3 Mini 128k Instruct |
|---|---|---|
| Terminal-Bench | 42.7% | — |
| Vending-Bench 2 | -23.16 | — |
Reasoning Phi 3 Mini 128k Instruct leads
MiniMax-M2.5: 17.6 (#281), Phi 3 Mini 128k Instruct: 18.7 (#254)
| Benchmark | MiniMax-M2.5 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1028 |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 55.2% | — |
| NYT Connections (extended) | 16.8% | — |
| ARC-AGI-1 | 63.7% | — |
| Epoch Capabilities Index | 146.68 | — |
Math Phi 3 Mini 128k Instruct leads
MiniMax-M2.5: 25.8 (#242), Phi 3 Mini 128k Instruct: 29.2 (#220)
| Benchmark | MiniMax-M2.5 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Math | 1378 | 1089 |
| ProofBench | 4% | — |
Knowledge MiniMax-M2.5 leads
MiniMax-M2.5: 38.6 (#132), Phi 3 Mini 128k Instruct: 26.3 (#251)
| Benchmark | MiniMax-M2.5 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Expert | 1378 | 984 |
| Vectara Hallucination Rate | 9.1% | — |
Multilingual MiniMax-M2.5 leads
MiniMax-M2.5: 47.3 (#147), Phi 3 Mini 128k Instruct: 25.4 (#280)
| Benchmark | MiniMax-M2.5 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Non-English | 1338 | 1000 |
| LMArena Chinese | 1392 | 1016 |
| LMArena French | 1363 | 1038 |
| LMArena German | 1361 | 1006 |
| LMArena Japanese | 1169 | 899 |
| LMArena Korean | 1232 | 856 |
| LMArena Russian | 1359 | 1004 |
| LMArena Spanish | 1354 | 1058 |
Instruction Following MiniMax-M2.5 leads
MiniMax-M2.5: 71.7 (#143), Phi 3 Mini 128k Instruct: 52.1 (#289)
| Benchmark | MiniMax-M2.5 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Instruction Following | 1353 | 1023 |
Long Context MiniMax-M2.5 leads
MiniMax-M2.5: 37.4 (#211), Phi 3 Mini 128k Instruct: 30.3 (#284)
| Benchmark | MiniMax-M2.5 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Longer Query | 1367 | 996 |
| CL-bench | 11.4% | — |
| CL-bench Life | 6.3% | — |
Writing & Preference MiniMax-M2.5 leads
MiniMax-M2.5: 54.1 (#149), Phi 3 Mini 128k Instruct: 27.3 (#296)
| Benchmark | MiniMax-M2.5 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Text | 1359 | 1050 |
| LMArena Creative Writing | 1331 | 1024 |
| LMArena Multi-Turn | 1364 | 989 |
| EQ-Bench Creative Writing | 1361 | — |
Frequently asked questions
Is MiniMax-M2.5 better than Phi 3 Mini 128k Instruct?
MiniMax-M2.5 is the stronger model overall, scoring 38.1 to 29.1 on the Noometry Index.
Is MiniMax-M2.5 or Phi 3 Mini 128k Instruct better for coding?
MiniMax-M2.5 scores higher on coding benchmarks: 47.9 versus 28.3 in the Noometry coding category.
How many benchmarks do MiniMax-M2.5 and Phi 3 Mini 128k Instruct share?
17 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.