Model comparison
MiniMax-M3 vs o3-pro
MiniMax-M3 and o3-pro score almost the same on the Noometry Index (43.8 vs 42.9), so choose on price, context window or the category you care about most.
Last verified . 3 shared benchmarks.
MiniMaxSummary
- They share 3 benchmarks with published results for both. MiniMax-M3 scores higher in 3 categories and o3-pro in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 29.5.
- The biggest single-benchmark swing is DTBench: 78.9% for MiniMax-M3 and 86.9% for o3-pro.
- MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $20 / $80 for o3-pro.
- MiniMax-M3 accepts more context: 1M tokens versus 200K.
- MiniMax-M3 has downloadable open weights; the other is API-only.
Side by side
| MiniMax-M3 | o3-pro | |
|---|---|---|
| Provider | MiniMax | OpenAI |
| Noometry Index | 43.8 | 42.9 |
| Released | 2026-06-01 | 2025-06-10 |
| Weights | Open | Proprietary |
| Context window | 1M | 200K |
| Max output | 512K | 100K |
| Input $ / M tokens | $0.30 | $20 |
| Output $ / M tokens | $1.20 | $80 |
| Results tracked | 41 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
MiniMax-M3: 41.8 (#118), o3-pro: 55.5 (#24)
| Benchmark | MiniMax-M3 | o3-pro |
|---|---|---|
| FrontierCode | 14.7% | — |
| Aider Polyglot | — | 84.9% |
| LMArena WebDev | 1482 | — |
| SciCode | 47.1% | — |
| WeirdML | — | 58.2% |
| LMArena Coding | 1469 | — |
| ALE-Bench | 640.02 | — |
Agentic & Tool Use Not comparable
MiniMax-M3: 22.6 (#130), o3-pro: —
| Benchmark | MiniMax-M3 | o3-pro |
|---|---|---|
| APEX-Agents | 37.7% | — |
| OSWorld 2.0 | 4.6% | — |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 2,158 | — |
Reasoning MiniMax-M3 leads
MiniMax-M3: 30.1 (#87), o3-pro: 23.8 (#171)
| Benchmark | MiniMax-M3 | o3-pro |
|---|---|---|
| DTBench | 78.9% | 86.9% |
| LMCA | 33.7% | 38.5% |
| Epoch Capabilities Index | 146.95 | 147.42 |
| ARC-AGI-2 | — | 4.9% |
| SimpleBench | 45.8% | — |
| Kagi LLM Benchmark | — | 72.1% |
| NYT Connections (extended) | 65.1% | — |
| ARC-AGI-1 | — | 59.3% |
| CritPt | 3.7% | — |
| Chess Puzzles | 14% | — |
| LMArena Hard Prompts | 1447 | — |
| Mystery Game Puzzles | 8% | — |
| Surface Evolver Bench | 55% | — |
| ForecastBench | 61.4 | — |
Math Not comparable
MiniMax-M3: 40.0 (#95), o3-pro: —
| Benchmark | MiniMax-M3 | o3-pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| ProofBench | 18% | — |
| LMArena Math | 1429 | — |
Knowledge MiniMax-M3 leads
MiniMax-M3: 58.4 (#35), o3-pro: 29.5 (#238)
| Benchmark | MiniMax-M3 | o3-pro |
|---|---|---|
| GPQA Diamond | 90.9% | — |
| Confabulations | — | 14.2% |
| Vectara Hallucination Rate | — | 23.3% |
| LMArena Expert | 1461 | — |
Multimodal Not comparable
MiniMax-M3: 40.2 (#51), o3-pro: —
| Benchmark | MiniMax-M3 | o3-pro |
|---|---|---|
| LMArena Vision | 1253 | — |
| LMArena Document | 1435 | — |
Multilingual Not comparable
MiniMax-M3: 53.0 (#75), o3-pro: —
| Benchmark | MiniMax-M3 | o3-pro |
|---|---|---|
| LMArena Non-English | 1420 | — |
| LMArena Chinese | 1463 | — |
| LMArena French | 1447 | — |
| LMArena German | 1426 | — |
| LMArena Japanese | 1381 | — |
| LMArena Korean | 1372 | — |
| LMArena Russian | 1428 | — |
| LMArena Spanish | 1432 | — |
Instruction Following Not comparable
MiniMax-M3: 75.5 (#62), o3-pro: —
| Benchmark | MiniMax-M3 | o3-pro |
|---|---|---|
| LMArena Instruction Following | 1433 | — |
Long Context o3-pro leads
MiniMax-M3: 44.2 (#72), o3-pro: 72.2 (#1)
| Benchmark | MiniMax-M3 | o3-pro |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |
| LMArena Longer Query | 1445 | — |
Writing & Preference MiniMax-M3 leads
MiniMax-M3: 62.1 (#83), o3-pro: 57.1 (#133)
| Benchmark | MiniMax-M3 | o3-pro |
|---|---|---|
| LMArena Text | 1433 | — |
| LMArena Creative Writing | 1404 | — |
| Short-Story Creative Writing | — | 84.4% |
| EQ-Bench 4 | 1150 | — |
| LMArena Multi-Turn | 1442 | — |
Frequently asked questions
Is MiniMax-M3 better than o3-pro?
MiniMax-M3 and o3-pro score almost the same on the Noometry Index (43.8 vs 42.9), so choose on price, context window or the category you care about most.
Which is cheaper, MiniMax-M3 or o3-pro?
MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; o3-pro lists at $20 and $80.
Is MiniMax-M3 or o3-pro better for coding?
o3-pro scores higher on coding benchmarks: 55.5 versus 41.8 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M3 does, with 1M tokens against 200K.
How many benchmarks do MiniMax-M3 and o3-pro share?
3 benchmarks have published results for both models. MiniMax-M3 has 41 scored results on Noometry and o3-pro has 12.