# Claude 3 Sonnet vs MiniMax-M2.1

> MiniMax-M2.1 is the stronger model overall, scoring 38.4 to 28.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-sonnet-vs-minimax-m2-1
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Claude 3 Sonnet scores higher in 1 category and MiniMax-M2.1 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where MiniMax-M2.1 leads 35.6 to 10.0.
- MiniMax-M2.1 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3 Sonnet | MiniMax-M2.1 |
|---|---|---|
| Provider | Anthropic | MiniMax |
| Noometry Index | 28.8 | 38.4 |
| Rank | 311 | 177 |
| Context | — | 205K |
| Input $/M | — | $0.30 |
| Output $/M | — | $1.20 |
| Weights | Proprietary | Open |

## Coding

- Claude 3 Sonnet: 29.2 (#296)
- MiniMax-M2.1: 40.1 (#132)

| Benchmark | Claude 3 Sonnet | MiniMax-M2.1 |
|---|---|---|
| LMArena Coding | 1223 | 1421 |
| LMArena WebDev | — | 1384 |
| WeirdML | 10.2% | — |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
| ALE-Bench | — | 623.83 |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |

## Agentic & Tool Use

- Claude 3 Sonnet: —
- MiniMax-M2.1: 27.7 (#91)

| Benchmark | Claude 3 Sonnet | MiniMax-M2.1 |
|---|---|---|
| Terminal-Bench | — | 36.6% |

## Reasoning

- Claude 3 Sonnet: 19.7 (#232)
- MiniMax-M2.1: 15.8 (#301)

| Benchmark | Claude 3 Sonnet | MiniMax-M2.1 |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1410 |
| NYT Connections (extended) | — | 11.2% |
| DTBench | 53.6% | — |
| Epoch Capabilities Index | 120.69 | — |
| WinoGrande | 75.1% | — |

## Math

- Claude 3 Sonnet: 10.0 (#305)
- MiniMax-M2.1: 35.6 (#142)

| Benchmark | Claude 3 Sonnet | MiniMax-M2.1 |
|---|---|---|
| LMArena Math | 1213 | 1396 |
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| MATH Level 5 | 18.2% | — |

## Knowledge

- Claude 3 Sonnet: 21.1 (#271)
- MiniMax-M2.1: 37.7 (#143)

| Benchmark | Claude 3 Sonnet | MiniMax-M2.1 |
|---|---|---|
| LMArena Expert | 1173 | 1432 |
| GPQA Diamond | 40.6% | — |
| Vectara Hallucination Rate | — | 11.8% |
| MMLU | 75.9% | — |

## Multimodal

- Claude 3 Sonnet: 24.7 (#120)
- MiniMax-M2.1: —

| Benchmark | Claude 3 Sonnet | MiniMax-M2.1 |
|---|---|---|
| LMArena Vision | 984 | — |

## Multilingual

- Claude 3 Sonnet: 38.0 (#229)
- MiniMax-M2.1: 50.2 (#123)

| Benchmark | Claude 3 Sonnet | MiniMax-M2.1 |
|---|---|---|
| LMArena Non-English | 1205 | 1378 |
| LMArena Chinese | 1188 | 1430 |
| LMArena French | 1228 | 1405 |
| LMArena German | 1204 | 1380 |
| LMArena Japanese | 1131 | 1287 |
| LMArena Korean | 1128 | 1297 |
| LMArena Russian | 1227 | 1386 |
| LMArena Spanish | 1204 | 1396 |

## Instruction Following

- Claude 3 Sonnet: 63.1 (#230)
- MiniMax-M2.1: 74.0 (#108)

| Benchmark | Claude 3 Sonnet | MiniMax-M2.1 |
|---|---|---|
| LMArena Instruction Following | 1200 | 1399 |

## Long Context

- Claude 3 Sonnet: 36.7 (#223)
- MiniMax-M2.1: 43.2 (#98)

| Benchmark | Claude 3 Sonnet | MiniMax-M2.1 |
|---|---|---|
| LMArena Longer Query | 1211 | 1416 |

## Writing & Preference

- Claude 3 Sonnet: 42.3 (#233)
- MiniMax-M2.1: 58.5 (#114)

| Benchmark | Claude 3 Sonnet | MiniMax-M2.1 |
|---|---|---|
| LMArena Text | 1218 | 1392 |
| LMArena Creative Writing | 1186 | 1362 |
| LMArena Multi-Turn | 1227 | 1396 |

## FAQ

### Is Claude 3 Sonnet better than MiniMax-M2.1?

MiniMax-M2.1 is the stronger model overall, scoring 38.4 to 28.8 on the Noometry Index.

### Is Claude 3 Sonnet or MiniMax-M2.1 better for coding?

MiniMax-M2.1 scores higher on coding benchmarks: 40.1 versus 29.2 in the Noometry coding category.

### How many benchmarks do Claude 3 Sonnet and MiniMax-M2.1 share?

17 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and MiniMax-M2.1 has 22.