Model comparison
Claude Opus 4 vs MiniMax-M3
Claude Opus 4 and MiniMax-M3 score almost the same on the Noometry Index (43.1 vs 43.8), so choose on price, context window or the category you care about most.
Last verified . 26 shared benchmarks.
MiniMaxSummary
- They share 26 benchmarks with published results for both. Claude Opus 4 scores higher in 4 categories and MiniMax-M3 in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 44.0.
- The biggest single-benchmark swing is GPQA Diamond: 76.3% for Claude Opus 4 and 90.9% for MiniMax-M3.
- MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $15 / $75 for Claude Opus 4.
- 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 | MiniMax-M3 | |
|---|---|---|
| Provider | Anthropic | MiniMax |
| Noometry Index | 43.1 | 43.8 |
| Released | 2025-05-22 | 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 | 56 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4 leads
Claude Opus 4: 47.2 (#62), MiniMax-M3: 41.8 (#118)
| Benchmark | Claude Opus 4 | MiniMax-M3 |
|---|---|---|
| LMArena Coding | 1442 | 1469 |
| SWE-bench Verified | 70.7% | — |
| FrontierCode | — | 14.7% |
| SWE-bench Verified (bash only) | 67.6% | — |
| Aider Polyglot | 72% | — |
| LMArena WebDev | — | 1482 |
| SciCode | — | 47.1% |
| GSO | 6.9% | — |
| WeirdML | 43.7% | — |
| ALE-Bench | — | 640.02 |
| AlgoTune | 1.33 | — |
Agentic & Tool Use Claude Opus 4 leads
Claude Opus 4: 34.8 (#42), MiniMax-M3: 22.6 (#130)
| Benchmark | Claude Opus 4 | MiniMax-M3 |
|---|---|---|
| APEX-Agents | — | 37.7% |
| OSWorld 2.0 | — | 4.6% |
| Cybench | 38% | — |
| DeepResearch Bench | 46.8% | — |
| GBAEval | — | 0.9% |
| LMArena Search | 1127 | — |
| METR Time Horizons | 63.9% | — |
| Vending-Bench 2 | — | 2,158 |
Reasoning MiniMax-M3 leads
Claude Opus 4: 27.3 (#121), MiniMax-M3: 30.1 (#87)
| Benchmark | Claude Opus 4 | MiniMax-M3 |
|---|---|---|
| SimpleBench | 58.8% | 45.8% |
| CritPt | 0.3% | 3.7% |
| LMArena Hard Prompts | 1399 | 1447 |
| DTBench | 81.6% | 78.9% |
| LMCA | 37.4% | 33.7% |
| Epoch Capabilities Index | 142.67 | 146.95 |
| ForecastBench | 61.1 | 61.4 |
| ARC-AGI-2 | 8.6% | — |
| Kagi LLM Benchmark | 74.3% | — |
| NYT Connections (extended) | — | 65.1% |
| ARC-AGI-1 | 35.7% | — |
| Chess Puzzles | — | 14% |
| EnigmaEval | 5.6% | — |
| Mystery Game Puzzles | — | 8% |
| Surface Evolver Bench | — | 55% |
Math Claude Opus 4 leads
Claude Opus 4: 42.0 (#86), MiniMax-M3: 40.0 (#95)
| Benchmark | Claude Opus 4 | MiniMax-M3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 64.4% | 71.1% |
| LMArena Math | 1390 | 1429 |
| ProofBench | — | 18% |
| Omni-MATH | 61.6% | — |
| MATH Level 5 | 85% | — |
| FrontierMath (Feb 2025 set) | 4.5% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge MiniMax-M3 leads
Claude Opus 4: 44.0 (#88), MiniMax-M3: 58.4 (#35)
| Benchmark | Claude Opus 4 | MiniMax-M3 |
|---|---|---|
| GPQA Diamond | 76.3% | 90.9% |
| LMArena Expert | 1386 | 1461 |
| Humanity's Last Exam | 10.7% | — |
| MMLU-Pro | 87.5% | — |
| Confabulations | 15.9% | — |
| Vectara Hallucination Rate | 12% | — |
| GPQA (HELM) | 70.8% | — |
Multimodal MiniMax-M3 leads
Claude Opus 4: 31.5 (#106), MiniMax-M3: 40.2 (#51)
| Benchmark | Claude Opus 4 | MiniMax-M3 |
|---|---|---|
| LMArena Vision | 1192 | 1253 |
| GeoBench | 49% | — |
| VPCT | 38% | — |
| LMArena Document | — | 1435 |
Multilingual MiniMax-M3 leads
Claude Opus 4: 48.8 (#138), MiniMax-M3: 53.0 (#75)
| Benchmark | Claude Opus 4 | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1362 | 1420 |
| LMArena Chinese | 1386 | 1463 |
| LMArena French | 1372 | 1447 |
| LMArena German | 1391 | 1426 |
| LMArena Japanese | 1331 | 1381 |
| LMArena Korean | 1321 | 1372 |
| LMArena Russian | 1392 | 1428 |
| LMArena Spanish | 1389 | 1432 |
Instruction Following Claude Opus 4 leads
Claude Opus 4: 77.1 (#28), MiniMax-M3: 75.5 (#62)
| Benchmark | Claude Opus 4 | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1406 | 1433 |
| IFEval | 91.8% | — |
Long Context MiniMax-M3 leads
Claude Opus 4: 39.6 (#172), MiniMax-M3: 44.2 (#72)
| Benchmark | Claude Opus 4 | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1422 | 1445 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference Too close to call
Claude Opus 4: 61.2 (#89), MiniMax-M3: 62.1 (#83)
| Benchmark | Claude Opus 4 | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1377 | 1433 |
| LMArena Creative Writing | 1387 | 1404 |
| LMArena Multi-Turn | 1396 | 1442 |
| Short-Story Creative Writing | 83.6% | — |
| EQ-Bench Creative Writing | 1580 | — |
| WildBench | 85.2% | — |
| EQ-Bench 4 | — | 1150 |
Frequently asked questions
Is Claude Opus 4 better than MiniMax-M3?
Claude Opus 4 and MiniMax-M3 score almost the same on the Noometry Index (43.1 vs 43.8), so choose on price, context window or the category you care about most.
Which is cheaper, Claude Opus 4 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 lists at $15 and $75.
Is Claude Opus 4 or MiniMax-M3 better for coding?
Claude Opus 4 scores higher on coding benchmarks: 47.2 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 and MiniMax-M3 share?
26 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and MiniMax-M3 has 41.