# Claude Sonnet 5.5 vs MiniMax-M3

> Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 43.8 on the Noometry Index. MiniMax-M3 costs 7.6× less per token, which makes it the better buy when Claude Sonnet 5.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-sonnet-5-5-vs-minimax-m3
- Last updated: 2026-10-12
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. Claude Sonnet 5.5 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 Sonnet 5.5 leads 87.9 to 40.0.
- The biggest single-benchmark swing is ProofBench: 100% for Claude Sonnet 5.5 and 18% for MiniMax-M3.
- MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.5.
- MiniMax-M3 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Sonnet 5.5 | MiniMax-M3 |
|---|---|---|
| Provider | Anthropic | MiniMax |
| Noometry Index | 61.9 | 43.8 |
| Rank | 10 | 85 |
| Context | 1M | 1M |
| Input $/M | $2 | $0.30 |
| Output $/M | $10 | $1.20 |
| Weights | Proprietary | Open |

## Coding

- Claude Sonnet 5.5: 67.3 (#6)
- MiniMax-M3: 41.8 (#118)

| Benchmark | Claude Sonnet 5.5 | MiniMax-M3 |
|---|---|---|
| FrontierCode | 52.1% | 14.7% |
| LMArena WebDev | 1774 | 1482 |
| SciCode | 61% | 47.1% |
| LMArena Coding | 1513 | 1469 |
| ALE-Bench | 1,819 | 640.02 |
| CursorBench | 55.5% | — |
| FrontierSWE | 61.9% | — |

## Agentic & Tool Use

- Claude Sonnet 5.5: 45.0 (#16)
- MiniMax-M3: 22.6 (#130)

| Benchmark | Claude Sonnet 5.5 | MiniMax-M3 |
|---|---|---|
| APEX-Agents | 75.5% | 37.7% |
| OSWorld 2.0 | — | 4.6% |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 2,158 |

## Reasoning

- Claude Sonnet 5.5: 54.0 (#28)
- MiniMax-M3: 30.1 (#87)

| Benchmark | Claude Sonnet 5.5 | MiniMax-M3 |
|---|---|---|
| NYT Connections (extended) | 80.5% | 65.1% |
| CritPt | 31.4% | 3.7% |
| LMArena Hard Prompts | 1495 | 1447 |
| Mystery Game Puzzles | 65% | 8% |
| Epoch Capabilities Index | 165.03 | 146.95 |
| SimpleBench | — | 45.8% |
| Chess Puzzles | — | 14% |
| DTBench | — | 78.9% |
| LMCA | — | 33.7% |
| Surface Evolver Bench | — | 55% |
| ForecastBench | — | 61.4 |

## Math

- Claude Sonnet 5.5: 87.9 (#6)
- MiniMax-M3: 40.0 (#95)

| Benchmark | Claude Sonnet 5.5 | MiniMax-M3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 71.1% |
| ProofBench | 100% | 18% |
| LMArena Math | 1510 | 1429 |
| FrontierMath (Tiers 1-3) | 88.8% | — |
| FrontierMath Tier 4 | 80.5% | — |
| FrontierMath Erdős | 2.9% | — |

## Knowledge

- Claude Sonnet 5.5: 66.0 (#12)
- MiniMax-M3: 58.4 (#35)

| Benchmark | Claude Sonnet 5.5 | MiniMax-M3 |
|---|---|---|
| GPQA Diamond | 95.6% | 90.9% |
| LMArena Expert | 1540 | 1461 |
| SimpleQA Verified | 46.5% | — |

## Multimodal

- Claude Sonnet 5.5: 51.5 (#6)
- MiniMax-M3: 40.2 (#51)

| Benchmark | Claude Sonnet 5.5 | MiniMax-M3 |
|---|---|---|
| LMArena Vision | 1289 | 1253 |
| Furniture Assembly | 75% | — |
| LMArena Document | — | 1435 |

## Multilingual

- Claude Sonnet 5.5: 55.3 (#30)
- MiniMax-M3: 53.0 (#75)

| Benchmark | Claude Sonnet 5.5 | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1452 | 1420 |
| LMArena Chinese | 1522 | 1463 |
| LMArena Russian | 1451 | 1428 |
| LMArena French | — | 1447 |
| LMArena German | — | 1426 |
| LMArena Japanese | — | 1381 |
| LMArena Korean | — | 1372 |
| LMArena Spanish | — | 1432 |

## Instruction Following

- Claude Sonnet 5.5: 78.3 (#11)
- MiniMax-M3: 75.5 (#62)

| Benchmark | Claude Sonnet 5.5 | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1495 | 1433 |

## Long Context

- Claude Sonnet 5.5: 45.9 (#28)
- MiniMax-M3: 44.2 (#72)

| Benchmark | Claude Sonnet 5.5 | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1498 | 1445 |

## Writing & Preference

- Claude Sonnet 5.5: 66.0 (#40)
- MiniMax-M3: 62.1 (#83)

| Benchmark | Claude Sonnet 5.5 | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1471 | 1433 |
| LMArena Creative Writing | 1465 | 1404 |
| LMArena Multi-Turn | 1474 | 1442 |
| EQ-Bench 4 | — | 1150 |

## FAQ

### Is Claude Sonnet 5.5 better than MiniMax-M3?

Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 43.8 on the Noometry Index. MiniMax-M3 costs 7.6× less per token, which makes it the better buy when Claude Sonnet 5.5's lead doesn't matter for your workload.

### Which is cheaper, Claude Sonnet 5.5 or MiniMax-M3?

MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Claude Sonnet 5.5 lists at $2 and $10.

### Is Claude Sonnet 5.5 or MiniMax-M3 better for coding?

Claude Sonnet 5.5 scores higher on coding benchmarks: 67.3 versus 41.8 in the Noometry coding category.

### Which has the bigger context window?

Both accept 1M tokens.

### How many benchmarks do Claude Sonnet 5.5 and MiniMax-M3 share?

25 benchmarks have published results for both models. Claude Sonnet 5.5 has 32 scored results on Noometry and MiniMax-M3 has 41.