Model comparison
MiniMax-M2.5 vs o1-mini
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 34.0 on the Noometry Index.
Last verified . 20 shared benchmarks.
MiniMaxSummary
- They share 20 benchmarks with published results for both. MiniMax-M2.5 scores higher in 7 categories and o1-mini in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiniMax-M2.5 leads 48.1 to 35.5.
- The biggest single-benchmark swing is ARC-AGI-1: 63.7% for MiniMax-M2.5 and 14% for o1-mini.
- MiniMax-M2.5 has downloadable open weights; the other is API-only.
Side by side
| MiniMax-M2.5 | o1-mini | |
|---|---|---|
| Provider | MiniMax | OpenAI |
| Noometry Index | 38.3 | 34.0 |
| Released | 2026-02-12 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 33 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.5 leads
MiniMax-M2.5: 48.1 (#58), o1-mini: 35.5 (#224)
| Benchmark | MiniMax-M2.5 | o1-mini |
|---|---|---|
| LMArena Coding | 1381 | 1362 |
| SWE-bench Verified (bash only) | 75.8% | — |
| Aider Polyglot | — | 32.9% |
| LMArena WebDev | 1387 | — |
| SWE-bench Multilingual | 68.3% | — |
| WeirdML | — | 36.3% |
| LiveBench Coding | — | 48% |
| ALE-Bench | 618.17 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |
Agentic & Tool Use MiniMax-M2.5 leads
MiniMax-M2.5: 30.4 (#77), o1-mini: 24.6 (#118)
| Benchmark | MiniMax-M2.5 | o1-mini |
|---|---|---|
| Terminal-Bench | 42.7% | — |
| Cybench | — | 10% |
| Vending-Bench 2 | -23.16 | — |
Reasoning MiniMax-M2.5 leads
MiniMax-M2.5: 17.5 (#292), o1-mini: 8.8 (#346)
| Benchmark | MiniMax-M2.5 | o1-mini |
|---|---|---|
| ARC-AGI-2 | 4.9% | 0.8% |
| ARC-AGI-1 | 63.7% | 14% |
| LMArena Hard Prompts | 1372 | 1333 |
| Epoch Capabilities Index | 146.68 | 135.82 |
| SimpleBench | — | 18.1% |
| Kagi LLM Benchmark | 55.2% | — |
| NYT Connections (extended) | 16.8% | — |
| LiveBench Reasoning | — | 72.3% |
| LiveBench Data Analysis | — | 57.9% |
| LiveBench | — | 57.8% |
Math o1-mini leads
MiniMax-M2.5: 26.9 (#253), o1-mini: 35.4 (#186)
| Benchmark | MiniMax-M2.5 | o1-mini |
|---|---|---|
| LMArena Math | 1378 | 1358 |
| OTIS Mock AIME 2024-2025 | — | 46.9% |
| ProofBench | 4% | — |
| LiveBench Math | — | 62% |
| MATH Level 5 | — | 89.2% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge MiniMax-M2.5 leads
MiniMax-M2.5: 39.2 (#135), o1-mini: 34.9 (#192)
| Benchmark | MiniMax-M2.5 | o1-mini |
|---|---|---|
| LMArena Expert | 1379 | 1316 |
| GPQA Diamond | — | 62.4% |
| Confabulations | — | 18.6% |
| Vectara Hallucination Rate | 9.1% | — |
Multilingual MiniMax-M2.5 leads
MiniMax-M2.5: 47.1 (#152), o1-mini: 43.6 (#182)
| Benchmark | MiniMax-M2.5 | o1-mini |
|---|---|---|
| LMArena Non-English | 1338 | 1289 |
| LMArena Chinese | 1393 | 1314 |
| LMArena French | 1362 | 1293 |
| LMArena German | 1362 | 1278 |
| LMArena Japanese | 1171 | 1245 |
| LMArena Korean | 1232 | 1223 |
| LMArena Russian | 1358 | 1283 |
| LMArena Spanish | 1354 | 1303 |
Instruction Following MiniMax-M2.5 leads
MiniMax-M2.5: 71.5 (#148), o1-mini: 66.7 (#206)
| Benchmark | MiniMax-M2.5 | o1-mini |
|---|---|---|
| LMArena Instruction Following | 1353 | 1304 |
| LiveBench Instruction Following | — | 65.4% |
Long Context o1-mini leads
MiniMax-M2.5: 37.5 (#216), o1-mini: 40.1 (#161)
| Benchmark | MiniMax-M2.5 | o1-mini |
|---|---|---|
| LMArena Longer Query | 1366 | 1320 |
| CL-bench | 11.4% | — |
| CL-bench Life | 6.3% | — |
Writing & Preference MiniMax-M2.5 leads
MiniMax-M2.5: 53.9 (#153), o1-mini: 48.4 (#202)
| Benchmark | MiniMax-M2.5 | o1-mini |
|---|---|---|
| LMArena Text | 1359 | 1317 |
| LMArena Creative Writing | 1331 | 1244 |
| LMArena Multi-Turn | 1364 | 1314 |
| Short-Story Creative Writing | — | 64.9% |
| EQ-Bench Creative Writing | 1361 | — |
| LiveBench Language | — | 40.9% |
Frequently asked questions
Is MiniMax-M2.5 better than o1-mini?
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 34.0 on the Noometry Index.
Is MiniMax-M2.5 or o1-mini better for coding?
MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 35.5 in the Noometry coding category.
How many benchmarks do MiniMax-M2.5 and o1-mini share?
20 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and o1-mini has 39.