Model comparison
Claude Fable 5.1 vs MiniMax-M3
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 43.8 on the Noometry Index. MiniMax-M3 costs 38× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.
Last verified . 34 shared benchmarks.
MiniMaxSummary
- They share 34 benchmarks with published results for both. Claude Fable 5.1 scores higher in 10 categories and MiniMax-M3 in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Fable 5.1 leads 89.6 to 40.0.
- The biggest single-benchmark swing is ProofBench: 100% for Claude Fable 5.1 and 18% for MiniMax-M3.
- MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $10 / $50 for Claude Fable 5.1.
- MiniMax-M3 has downloadable open weights; the other is API-only.
Side by side
| Claude Fable 5.1 | MiniMax-M3 | |
|---|---|---|
| Provider | Anthropic | MiniMax |
| Noometry Index | 69.0 | 43.8 |
| Released | 2026-09-01 | 2026-06-01 |
| Weights | Proprietary | Open |
| Context window | 1M | 1M |
| Max output | 128K | 512K |
| Input $ / M tokens | $10 | $0.30 |
| Output $ / M tokens | $50 | $1.20 |
| Results tracked | 52 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Fable 5.1 leads
Claude Fable 5.1: 74.7 (#1), MiniMax-M3: 41.8 (#118)
| Benchmark | Claude Fable 5.1 | MiniMax-M3 |
|---|---|---|
| FrontierCode | 50.9% | 14.7% |
| LMArena WebDev | 1744 | 1482 |
| SciCode | 63.1% | 47.1% |
| LMArena Coding | 1528 | 1469 |
| ALE-Bench | 2,143 | 640.02 |
| CursorBench | 51.8% | — |
| FrontierSWE | 56.3% | — |
| GSO | 88.2% | — |
| WeirdML | 92.9% | — |
| MirrorCode | 73.3% | — |
Agentic & Tool Use Claude Fable 5.1 leads
Claude Fable 5.1: 50.7 (#5), MiniMax-M3: 22.6 (#130)
| Benchmark | Claude Fable 5.1 | MiniMax-M3 |
|---|---|---|
| APEX-Agents | 68.6% | 37.7% |
| Vending-Bench 2 | 5,422 | 2,158 |
| OSWorld 2.0 | — | 4.6% |
| Remote Labor Index | 17.9% | — |
| GBAEval | — | 0.9% |
| GDP.pdf | 29.6% | — |
Reasoning Claude Fable 5.1 leads
Claude Fable 5.1: 76.7 (#7), MiniMax-M3: 30.1 (#87)
| Benchmark | Claude Fable 5.1 | MiniMax-M3 |
|---|---|---|
| NYT Connections (extended) | 90% | 65.1% |
| CritPt | 31.1% | 3.7% |
| Chess Puzzles | 47% | 14% |
| LMArena Hard Prompts | 1526 | 1447 |
| Mystery Game Puzzles | 58% | 8% |
| DTBench | 97.6% | 78.9% |
| LMCA | 65.5% | 33.7% |
| Epoch Capabilities Index | 164.7 | 146.95 |
| ARC-AGI-2 | 90% | — |
| SimpleBench | — | 45.8% |
| ARC-AGI-1 | 97.5% | — |
| EBR-Bench | 57.1% | — |
| Surface Evolver Bench | — | 55% |
| ForecastBench | — | 61.4 |
Math Claude Fable 5.1 leads
Claude Fable 5.1: 89.6 (#4), MiniMax-M3: 40.0 (#95)
| Benchmark | Claude Fable 5.1 | MiniMax-M3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 71.1% |
| ProofBench | 100% | 18% |
| LMArena Math | 1525 | 1429 |
| FrontierMath (Tiers 1-3) | 90.2% | — |
| FrontierMath Tier 4 | 87.8% | — |
| FrontierMath Erdős | 0% | — |
Knowledge Claude Fable 5.1 leads
Claude Fable 5.1: 69.6 (#6), MiniMax-M3: 58.4 (#35)
| Benchmark | Claude Fable 5.1 | MiniMax-M3 |
|---|---|---|
| LMArena Expert | 1535 | 1461 |
| GPQA Diamond | — | 90.9% |
| Humanity's Last Exam | 46.5% | — |
| SimpleQA Verified | 70.8% | — |
Multimodal Claude Fable 5.1 leads
Claude Fable 5.1: 53.9 (#4), MiniMax-M3: 40.2 (#51)
| Benchmark | Claude Fable 5.1 | MiniMax-M3 |
|---|---|---|
| LMArena Vision | 1318 | 1253 |
| LMArena Document | 1513 | 1435 |
| Blueprint-Bench 2 | 41.9% | — |
| Furniture Assembly | 70% | — |
Multilingual Claude Fable 5.1 leads
Claude Fable 5.1: 59.1 (#3), MiniMax-M3: 53.0 (#75)
| Benchmark | Claude Fable 5.1 | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1507 | 1420 |
| LMArena Chinese | 1586 | 1463 |
| LMArena French | 1525 | 1447 |
| LMArena German | 1500 | 1426 |
| LMArena Japanese | 1543 | 1381 |
| LMArena Korean | 1534 | 1372 |
| LMArena Russian | 1521 | 1428 |
| LMArena Spanish | 1516 | 1432 |
Instruction Following Claude Fable 5.1 leads
Claude Fable 5.1: 79.2 (#6), MiniMax-M3: 75.5 (#62)
| Benchmark | Claude Fable 5.1 | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1517 | 1433 |
Long Context Claude Fable 5.1 leads
Claude Fable 5.1: 46.7 (#20), MiniMax-M3: 44.2 (#72)
| Benchmark | Claude Fable 5.1 | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1522 | 1445 |
Writing & Preference Claude Fable 5.1 leads
Claude Fable 5.1: 79.2 (#2), MiniMax-M3: 62.1 (#83)
| Benchmark | Claude Fable 5.1 | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1510 | 1433 |
| LMArena Creative Writing | 1507 | 1404 |
| LMArena Multi-Turn | 1492 | 1442 |
| EQ-Bench Creative Writing | 2162 | — |
| EQ-Bench 4 | — | 1150 |
Frequently asked questions
Is Claude Fable 5.1 better than MiniMax-M3?
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 43.8 on the Noometry Index. MiniMax-M3 costs 38× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.
Which is cheaper, Claude Fable 5.1 or MiniMax-M3?
MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Claude Fable 5.1 lists at $10 and $50.
Is Claude Fable 5.1 or MiniMax-M3 better for coding?
Claude Fable 5.1 scores higher on coding benchmarks: 74.7 versus 41.8 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do Claude Fable 5.1 and MiniMax-M3 share?
34 benchmarks have published results for both models. Claude Fable 5.1 has 52 scored results on Noometry and MiniMax-M3 has 41.