# Claude Sonnet 4 vs MiniMax-M2.7

> Claude Sonnet 4 is the stronger model overall, scoring 40.6 to 37.4 on the Noometry Index. MiniMax-M2.7 costs 11× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-sonnet-4-vs-minimax-m2-7
- Last updated: 2026-10-10
- Shared benchmarks: 23

## Summary

- They share 23 benchmarks with published results for both. Claude Sonnet 4 scores higher in 5 categories and MiniMax-M2.7 in 4 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 4 leads 41.5 to 24.9.
- The biggest single-benchmark swing is WeirdML: 46.1% for Claude Sonnet 4 and 37% for MiniMax-M2.7.
- MiniMax-M2.7 is cheaper at $0.30 / $1.20 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
- MiniMax-M2.7 accepts more context: 205K tokens versus 200K.
- MiniMax-M2.7 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Sonnet 4 | MiniMax-M2.7 |
|---|---|---|
| Provider | Anthropic | MiniMax |
| Noometry Index | 40.6 | 37.4 |
| Rank | 139 | 188 |
| Context | 200K | 205K |
| Input $/M | $3 | $0.30 |
| Output $/M | $15 | $1.20 |
| Weights | Proprietary | Open |

## Coding

- Claude Sonnet 4: 44.0 (#70)
- MiniMax-M2.7: 41.4 (#115)

| Benchmark | Claude Sonnet 4 | MiniMax-M2.7 |
|---|---|---|
| SciCode | 40% | 47% |
| WeirdML | 46.1% | 37% |
| LMArena Coding | 1414 | 1454 |
| ALE-Bench | 655.35 | 599.25 |
| SWE-bench Verified (bash only) | 64.9% | — |
| Aider Polyglot | 61.3% | — |
| LMArena WebDev | — | 1397 |
| GSO | 4.9% | — |

## Agentic & Tool Use

- Claude Sonnet 4: 38.3 (#29)
- MiniMax-M2.7: 24.9 (#103)

| Benchmark | Claude Sonnet 4 | MiniMax-M2.7 |
|---|---|---|
| Terminal-Bench | — | 45.1% |
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| ExploitBench | — | 13.3% |
| GBAEval | — | 0% |
| METR Time Horizons | 62% | — |

## Reasoning

- Claude Sonnet 4: 23.0 (#169)
- MiniMax-M2.7: 19.0 (#248)

| Benchmark | Claude Sonnet 4 | MiniMax-M2.7 |
|---|---|---|
| CritPt | 0.3% | 0.6% |
| LMArena Hard Prompts | 1372 | 1422 |
| Epoch Capabilities Index | 141.69 | 145.84 |
| ARC-AGI-2 | 5.9% | — |
| SimpleBench | 45.5% | — |
| Kagi LLM Benchmark | 73% | — |
| NYT Connections (extended) | — | 24.7% |
| ARC-AGI-1 | 40% | — |
| EnigmaEval | 3.1% | — |
| Thematic Generalization | — | 39.3% |
| DTBench | 77.1% | — |
| LMCA | 29% | — |
| ForecastBench | 60.2 | — |

## Math

- Claude Sonnet 4: 41.5 (#71)
- MiniMax-M2.7: 24.9 (#254)

| Benchmark | Claude Sonnet 4 | MiniMax-M2.7 |
|---|---|---|
| LMArena Math | 1375 | 1420 |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| ProofBench | — | 3% |
| Omni-MATH | 60.2% | — |
| MATH Level 5 | 84.4% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |

## Knowledge

- Claude Sonnet 4: 41.6 (#99)
- MiniMax-M2.7: 37.1 (#151)

| Benchmark | Claude Sonnet 4 | MiniMax-M2.7 |
|---|---|---|
| Vectara Hallucination Rate | 10.3% | 12.9% |
| LMArena Expert | 1371 | 1443 |
| GPQA Diamond | 79.2% | — |
| Humanity's Last Exam | 7.8% | — |
| MMLU-Pro | 84.3% | — |
| Confabulations | 13.2% | — |
| GPQA (HELM) | 70.6% | — |

## Multimodal

- Claude Sonnet 4: 25.6 (#116)
- MiniMax-M2.7: —

| Benchmark | Claude Sonnet 4 | MiniMax-M2.7 |
|---|---|---|
| LMArena Vision | 1191 | — |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |

## Multilingual

- Claude Sonnet 4: 46.9 (#151)
- MiniMax-M2.7: 50.5 (#120)

| Benchmark | Claude Sonnet 4 | MiniMax-M2.7 |
|---|---|---|
| LMArena Non-English | 1333 | 1382 |
| LMArena Chinese | 1351 | 1439 |
| LMArena French | 1364 | 1422 |
| LMArena German | 1331 | 1398 |
| LMArena Japanese | 1301 | 1261 |
| LMArena Korean | 1293 | 1313 |
| LMArena Russian | 1355 | 1383 |
| LMArena Spanish | 1356 | 1403 |

## Instruction Following

- Claude Sonnet 4: 71.8 (#141)
- MiniMax-M2.7: 74.2 (#101)

| Benchmark | Claude Sonnet 4 | MiniMax-M2.7 |
|---|---|---|
| LMArena Instruction Following | 1375 | 1404 |
| IFEval | 84% | — |

## Long Context

- Claude Sonnet 4: 33.6 (#254)
- MiniMax-M2.7: 43.3 (#94)

| Benchmark | Claude Sonnet 4 | MiniMax-M2.7 |
|---|---|---|
| LMArena Longer Query | 1398 | 1419 |
| Fiction.LiveBench | 46.9% | — |

## Writing & Preference

- Claude Sonnet 4: 57.3 (#127)
- MiniMax-M2.7: 59.1 (#107)

| Benchmark | Claude Sonnet 4 | MiniMax-M2.7 |
|---|---|---|
| LMArena Text | 1351 | 1404 |
| LMArena Creative Writing | 1345 | 1354 |
| LMArena Multi-Turn | 1376 | 1413 |
| Short-Story Creative Writing | 81.4% | — |
| EQ-Bench Creative Writing | 1483 | — |
| WildBench | 83.8% | — |

## FAQ

### Is Claude Sonnet 4 better than MiniMax-M2.7?

Claude Sonnet 4 is the stronger model overall, scoring 40.6 to 37.4 on the Noometry Index. MiniMax-M2.7 costs 11× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.

### Which is cheaper, Claude Sonnet 4 or MiniMax-M2.7?

MiniMax-M2.7 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Claude Sonnet 4 lists at $3 and $15.

### Is Claude Sonnet 4 or MiniMax-M2.7 better for coding?

Claude Sonnet 4 scores higher on coding benchmarks: 44.0 versus 41.4 in the Noometry coding category.

### Which has the bigger context window?

MiniMax-M2.7 does, with 205K tokens against 200K.

### How many benchmarks do Claude Sonnet 4 and MiniMax-M2.7 share?

23 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and MiniMax-M2.7 has 30.