Model comparison
Claude Opus 4.1 vs MiniMax-M3
MiniMax-M3 is the stronger model overall, scoring 43.8 to 41.0 on the Noometry Index.
Last verified . 28 shared benchmarks.
MiniMaxSummary
- They share 28 benchmarks with published results for both. Claude Opus 4.1 scores higher in 6 categories and MiniMax-M3 in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where MiniMax-M3 leads 40.0 to 22.3.
- The biggest single-benchmark swing is SimpleBench: 60% for Claude Opus 4.1 and 45.8% for MiniMax-M3.
- MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $15 / $75 for Claude Opus 4.1.
- MiniMax-M3 accepts more context: 1M tokens versus 200K.
- MiniMax-M3 has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 4.1 | MiniMax-M3 | |
|---|---|---|
| Provider | Anthropic | MiniMax |
| Noometry Index | 41.0 | 43.8 |
| Released | 2025-08-05 | 2026-06-01 |
| Weights | Proprietary | Open |
| Context window | 200K | 1M |
| Max output | 32K | 512K |
| Input $ / M tokens | $15 | $0.30 |
| Output $ / M tokens | $75 | $1.20 |
| Results tracked | 48 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4.1 leads
Claude Opus 4.1: 44.4 (#73), MiniMax-M3: 41.8 (#118)
| Benchmark | Claude Opus 4.1 | MiniMax-M3 |
|---|---|---|
| LMArena WebDev | 1390 | 1482 |
| LMArena Coding | 1479 | 1469 |
| ALE-Bench | 674.77 | 640.02 |
| SWE-bench Verified | 73.3% | — |
| FrontierCode | — | 14.7% |
| SciCode | — | 47.1% |
| WeirdML | 45.9% | — |
| AlgoTune | 1.34 | — |
Agentic & Tool Use Claude Opus 4.1 leads
Claude Opus 4.1: 35.0 (#41), MiniMax-M3: 22.6 (#130)
| Benchmark | Claude Opus 4.1 | MiniMax-M3 |
|---|---|---|
| Terminal-Bench | 38% | — |
| APEX-Agents | — | 37.7% |
| OSWorld 2.0 | — | 4.6% |
| GDPval | 43.6% | — |
| Cybench | 42% | — |
| DeepResearch Bench | 48.3% | — |
| GBAEval | — | 0.9% |
| LMArena Search | 1148 | — |
| METR Time Horizons | 66.8% | — |
| Vending-Bench 2 | — | 2,158 |
Reasoning Claude Opus 4.1 leads
Claude Opus 4.1: 32.2 (#76), MiniMax-M3: 30.1 (#87)
| Benchmark | Claude Opus 4.1 | MiniMax-M3 |
|---|---|---|
| SimpleBench | 60% | 45.8% |
| Chess Puzzles | 7% | 14% |
| LMArena Hard Prompts | 1443 | 1447 |
| Mystery Game Puzzles | 21% | 8% |
| DTBench | 80% | 78.9% |
| LMCA | 37.1% | 33.7% |
| Epoch Capabilities Index | 144.12 | 146.95 |
| ForecastBench | 62 | 61.4 |
| NYT Connections (extended) | — | 65.1% |
| CritPt | — | 3.7% |
| EnigmaEval | 7.2% | — |
| EBR-Bench | 7.9% | — |
| Surface Evolver Bench | — | 55% |
Math MiniMax-M3 leads
Claude Opus 4.1: 22.3 (#277), MiniMax-M3: 40.0 (#95)
| Benchmark | Claude Opus 4.1 | MiniMax-M3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 68.9% | 71.1% |
| LMArena Math | 1431 | 1429 |
| FrontierMath (Tiers 1-3) | 12.6% | — |
| FrontierMath Tier 4 | 2.4% | — |
| ProofBench | — | 18% |
| FrontierMath (Feb 2025 set) | 7.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge MiniMax-M3 leads
Claude Opus 4.1: 42.0 (#101), MiniMax-M3: 58.4 (#35)
| Benchmark | Claude Opus 4.1 | MiniMax-M3 |
|---|---|---|
| GPQA Diamond | 77.3% | 90.9% |
| LMArena Expert | 1439 | 1461 |
| Humanity's Last Exam | 11.5% | — |
| Confabulations | 17.1% | — |
| Vectara Hallucination Rate | 11.8% | — |
Multimodal MiniMax-M3 leads
Claude Opus 4.1: 26.8 (#119), MiniMax-M3: 40.2 (#51)
| Benchmark | Claude Opus 4.1 | MiniMax-M3 |
|---|---|---|
| LMArena Vision | — | 1253 |
| VPCT | 35% | — |
| LMArena Document | — | 1435 |
Multilingual MiniMax-M3 leads
Claude Opus 4.1: 52.0 (#95), MiniMax-M3: 53.0 (#75)
| Benchmark | Claude Opus 4.1 | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1405 | 1420 |
| LMArena Chinese | 1427 | 1463 |
| LMArena French | 1431 | 1447 |
| LMArena German | 1413 | 1426 |
| LMArena Japanese | 1378 | 1381 |
| LMArena Korean | 1380 | 1372 |
| LMArena Russian | 1422 | 1428 |
| LMArena Spanish | 1448 | 1432 |
Instruction Following Too close to call
Claude Opus 4.1: 75.6 (#58), MiniMax-M3: 75.5 (#62)
| Benchmark | Claude Opus 4.1 | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1435 | 1433 |
Long Context Too close to call
Claude Opus 4.1: 44.5 (#63), MiniMax-M3: 44.2 (#72)
| Benchmark | Claude Opus 4.1 | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1455 | 1445 |
Writing & Preference Too close to call
Claude Opus 4.1: 62.4 (#74), MiniMax-M3: 62.1 (#83)
| Benchmark | Claude Opus 4.1 | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1419 | 1433 |
| LMArena Creative Writing | 1412 | 1404 |
| LMArena Multi-Turn | 1444 | 1442 |
| Short-Story Creative Writing | 84.7% | — |
| EQ-Bench 4 | — | 1150 |
Frequently asked questions
Is Claude Opus 4.1 better than MiniMax-M3?
MiniMax-M3 is the stronger model overall, scoring 43.8 to 41.0 on the Noometry Index.
Which is cheaper, Claude Opus 4.1 or MiniMax-M3?
MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Claude Opus 4.1 lists at $15 and $75.
Is Claude Opus 4.1 or MiniMax-M3 better for coding?
Claude Opus 4.1 scores higher on coding benchmarks: 44.4 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 Claude Opus 4.1 and MiniMax-M3 share?
28 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and MiniMax-M3 has 41.