# Claude Sonnet 4.5 vs MiniMax-M2

> Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 37.4 on the Noometry Index. MiniMax-M2 costs 11× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-sonnet-4-5-vs-minimax-m2
- Last updated: 2026-10-12
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 8 categories and MiniMax-M2 in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude Sonnet 4.5 leads 66.5 to 53.0.
- The biggest single-benchmark swing is NYT Connections (extended): 37.3% for Claude Sonnet 4.5 and 14.8% for MiniMax-M2.
- MiniMax-M2 is cheaper at $0.30 / $1.20 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
- MiniMax-M2 accepts more context: 205K tokens versus 200K.
- MiniMax-M2 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Sonnet 4.5 | MiniMax-M2 |
|---|---|---|
| Provider | Anthropic | MiniMax |
| Noometry Index | 44.1 | 37.4 |
| Rank | 81 | 204 |
| Context | 200K | 205K |
| Input $/M | $3 | $0.30 |
| Output $/M | $15 | $1.20 |
| Weights | Proprietary | Open |

## Coding

- Claude Sonnet 4.5: 47.3 (#61)
- MiniMax-M2: 39.3 (#159)

| Benchmark | Claude Sonnet 4.5 | MiniMax-M2 |
|---|---|---|
| SWE-bench Verified (bash only) | 71.4% | 61% |
| LMArena WebDev | 1393 | 1297 |
| LMArena Coding | 1489 | 1370 |
| SWE-bench Verified | 71.3% | — |
| SWE-bench Multilingual | 67% | — |
| SciCode | 44.7% | — |
| GSO | 14.7% | — |
| WeirdML | 47.7% | — |
| ALE-Bench | 796.15 | — |
| AlgoTune | 1.52 | — |

## Agentic & Tool Use

- Claude Sonnet 4.5: 38.3 (#32)
- MiniMax-M2: 25.1 (#109)

| Benchmark | Claude Sonnet 4.5 | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | 46.5% | 30% |
| Vending-Bench 2 | 3,839 | 160.6 |
| Berkeley Function Calling Leaderboard | 73.2% | — |
| GDPval | 42.5% | — |
| Remote Labor Index | 2.1% | — |
| τ²-bench Airline | 72% | — |
| τ²-bench Banking | 25.3% | — |
| τ²-bench Retail | 72.4% | — |
| τ²-bench Telecom | 84.9% | — |
| Cybench | 60% | — |
| DeepResearch Bench | 52.6% | — |
| OSWorld | 62.9% | — |
| LMArena Search | 1159 | — |
| METR Time Horizons | 67.4% | — |

## Reasoning

- Claude Sonnet 4.5: 26.9 (#125)
- MiniMax-M2: 19.4 (#258)

| Benchmark | Claude Sonnet 4.5 | MiniMax-M2 |
|---|---|---|
| Kagi LLM Benchmark | 57.9% | 57.8% |
| NYT Connections (extended) | 37.3% | 14.8% |
| LMArena Hard Prompts | 1462 | 1357 |
| ARC-AGI-2 | 13.6% | — |
| SimpleBench | 54.3% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | 12% | — |
| EnigmaEval | 6% | — |
| EBR-Bench | 2.4% | — |
| Mystery Game Puzzles | 17% | — |
| DTBench | 83.2% | — |
| LMCA | 38.8% | — |
| Epoch Capabilities Index | 146.84 | — |
| ForecastBench | 61.9 | — |

## Math

- Claude Sonnet 4.5: 32.3 (#216)
- MiniMax-M2: 37.3 (#160)

| Benchmark | Claude Sonnet 4.5 | MiniMax-M2 |
|---|---|---|
| LMArena Math | 1449 | 1352 |
| FrontierMath (Tiers 1-3) | 23.9% | — |
| FrontierMath Tier 4 | 2.4% | — |
| OTIS Mock AIME 2024-2025 | 77.8% | — |
| ProofBench | 19% | — |
| Omni-MATH | 55.3% | — |
| MATH Level 5 | 97.7% | — |
| FrontierMath (Feb 2025 set) | 15.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |

## Knowledge

- Claude Sonnet 4.5: 48.4 (#76)
- MiniMax-M2: 37.0 (#163)

| Benchmark | Claude Sonnet 4.5 | MiniMax-M2 |
|---|---|---|
| LMArena Expert | 1482 | 1337 |
| GPQA Diamond | 82.3% | — |
| Humanity's Last Exam | 13.7% | — |
| SimpleQA Verified | 30.7% | — |
| MMLU-Pro | 86.9% | — |
| Vectara Hallucination Rate | 12% | — |
| GPQA (HELM) | 68.6% | — |

## Multimodal

- Claude Sonnet 4.5: 34.8 (#89)
- MiniMax-M2: —

| Benchmark | Claude Sonnet 4.5 | MiniMax-M2 |
|---|---|---|
| VPCT | 39.8% | — |
| LMArena Document | 1450 | — |

## Multilingual

- Claude Sonnet 4.5: 53.4 (#69)
- MiniMax-M2: 45.3 (#171)

| Benchmark | Claude Sonnet 4.5 | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1425 | 1313 |
| LMArena Chinese | 1459 | 1366 |
| LMArena French | 1458 | 1335 |
| LMArena German | 1427 | 1355 |
| LMArena Russian | 1437 | 1331 |
| LMArena Spanish | 1457 | 1326 |
| LMArena Japanese | 1390 | — |
| LMArena Korean | 1403 | — |

## Instruction Following

- Claude Sonnet 4.5: 75.0 (#78)
- MiniMax-M2: 70.2 (#166)

| Benchmark | Claude Sonnet 4.5 | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1459 | 1328 |
| IFEval | 85% | — |

## Long Context

- Claude Sonnet 4.5: 45.2 (#46)
- MiniMax-M2: 40.5 (#153)

| Benchmark | Claude Sonnet 4.5 | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1476 | 1331 |

## Writing & Preference

- Claude Sonnet 4.5: 66.5 (#34)
- MiniMax-M2: 53.0 (#162)

| Benchmark | Claude Sonnet 4.5 | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1439 | 1340 |
| LMArena Creative Writing | 1442 | 1286 |
| LMArena Multi-Turn | 1465 | 1361 |
| EQ-Bench Creative Writing | 1678 | — |
| WildBench | 85.4% | — |

## FAQ

### Is Claude Sonnet 4.5 better than MiniMax-M2?

Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 37.4 on the Noometry Index. MiniMax-M2 costs 11× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

### Which is cheaper, Claude Sonnet 4.5 or MiniMax-M2?

MiniMax-M2 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.

### Is Claude Sonnet 4.5 or MiniMax-M2 better for coding?

Claude Sonnet 4.5 scores higher on coding benchmarks: 47.3 versus 39.3 in the Noometry coding category.

### Which has the bigger context window?

MiniMax-M2 does, with 205K tokens against 200K.

### How many benchmarks do Claude Sonnet 4.5 and MiniMax-M2 share?

21 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and MiniMax-M2 has 21.