Model comparison
Claude 3 Opus vs MiniMax-M3
MiniMax-M3 is the stronger model overall, scoring 43.8 to 29.5 on the Noometry Index.
Last verified . 26 shared benchmarks.
MiniMaxSummary
- They share 26 benchmarks with published results for both. Claude 3 Opus scores higher in 1 category and MiniMax-M3 in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 24.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.7% for Claude 3 Opus and 71.1% for MiniMax-M3.
- MiniMax-M3 has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Opus | MiniMax-M3 | |
|---|---|---|
| Provider | Anthropic | MiniMax |
| Noometry Index | 29.5 | 43.8 |
| Released | 2024-02-29 | 2026-06-01 |
| Weights | Proprietary | Open |
| Context window | — | 1M |
| Max output | — | 512K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 46 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M3 leads
Claude 3 Opus: 32.9 (#267), MiniMax-M3: 41.8 (#118)
| Benchmark | Claude 3 Opus | MiniMax-M3 |
|---|---|---|
| LMArena Coding | 1264 | 1469 |
| FrontierCode | — | 14.7% |
| LMArena WebDev | — | 1482 |
| SciCode | — | 47.1% |
| WeirdML | 19.2% | — |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 38.6% | — |
| BigCodeBench Complete | 57.4% | — |
| ALE-Bench | — | 640.02 |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Claude 3 Opus leads
Claude 3 Opus: 24.6 (#116), MiniMax-M3: 22.6 (#130)
| Benchmark | Claude 3 Opus | MiniMax-M3 |
|---|---|---|
| APEX-Agents | — | 37.7% |
| OSWorld 2.0 | — | 4.6% |
| Cybench | 10% | — |
| GBAEval | — | 0.9% |
| METR Time Horizons | 29.5% | — |
| Vending-Bench 2 | — | 2,158 |
Reasoning MiniMax-M3 leads
Claude 3 Opus: 14.6 (#324), MiniMax-M3: 30.1 (#87)
| Benchmark | Claude 3 Opus | MiniMax-M3 |
|---|---|---|
| SimpleBench | 23.5% | 45.8% |
| Chess Puzzles | 5% | 14% |
| LMArena Hard Prompts | 1245 | 1447 |
| DTBench | 61.6% | 78.9% |
| LMCA | 17% | 33.7% |
| Epoch Capabilities Index | 126.91 | 146.95 |
| ForecastBench | 58.4 | 61.4 |
| NYT Connections (extended) | — | 65.1% |
| CritPt | — | 3.7% |
| EnigmaEval | 0.8% | — |
| LiveBench Reasoning | 40.6% | — |
| Mystery Game Puzzles | — | 8% |
| LiveBench Data Analysis | 57.9% | — |
| Surface Evolver Bench | — | 55% |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |
Math MiniMax-M3 leads
Claude 3 Opus: 14.8 (#299), MiniMax-M3: 40.0 (#95)
| Benchmark | Claude 3 Opus | MiniMax-M3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 71.1% |
| LMArena Math | 1273 | 1429 |
| ProofBench | — | 18% |
| LiveBench Math | 43.6% | — |
| MATH Level 5 | 37.5% | — |
Knowledge MiniMax-M3 leads
Claude 3 Opus: 24.5 (#267), MiniMax-M3: 58.4 (#35)
| Benchmark | Claude 3 Opus | MiniMax-M3 |
|---|---|---|
| GPQA Diamond | 47.2% | 90.9% |
| LMArena Expert | 1223 | 1461 |
| SimpleQA Verified | 12.6% | — |
| Confabulations | 22.7% | — |
| MMLU | 84.6% | — |
Multimodal MiniMax-M3 leads
Claude 3 Opus: 27.1 (#116), MiniMax-M3: 40.2 (#51)
| Benchmark | Claude 3 Opus | MiniMax-M3 |
|---|---|---|
| LMArena Vision | 1023 | 1253 |
| LMArena Document | — | 1435 |
Multilingual MiniMax-M3 leads
Claude 3 Opus: 41.4 (#207), MiniMax-M3: 53.0 (#75)
| Benchmark | Claude 3 Opus | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1258 | 1420 |
| LMArena Chinese | 1248 | 1463 |
| LMArena French | 1275 | 1447 |
| LMArena German | 1258 | 1426 |
| LMArena Japanese | 1204 | 1381 |
| LMArena Korean | 1187 | 1372 |
| LMArena Russian | 1280 | 1428 |
| LMArena Spanish | 1246 | 1432 |
Instruction Following MiniMax-M3 leads
Claude 3 Opus: 64.1 (#228), MiniMax-M3: 75.5 (#62)
| Benchmark | Claude 3 Opus | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1248 | 1433 |
| LiveBench Instruction Following | 63.9% | — |
Long Context MiniMax-M3 leads
Claude 3 Opus: 38.2 (#202), MiniMax-M3: 44.2 (#72)
| Benchmark | Claude 3 Opus | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1259 | 1445 |
Writing & Preference MiniMax-M3 leads
Claude 3 Opus: 47.2 (#213), MiniMax-M3: 62.1 (#83)
| Benchmark | Claude 3 Opus | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1262 | 1433 |
| LMArena Creative Writing | 1235 | 1404 |
| LMArena Multi-Turn | 1275 | 1442 |
| EQ-Bench 4 | — | 1150 |
| LiveBench Language | 50.4% | — |
Frequently asked questions
Is Claude 3 Opus better than MiniMax-M3?
MiniMax-M3 is the stronger model overall, scoring 43.8 to 29.5 on the Noometry Index.
Is Claude 3 Opus or MiniMax-M3 better for coding?
MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and MiniMax-M3 share?
26 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and MiniMax-M3 has 41.