# Claude 2 vs MiniMax-M2

> MiniMax-M2 is the stronger model overall, scoring 36.9 to 24.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-2-vs-minimax-m2
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in math, where MiniMax-M2 leads 34.6 to 8.7.
- MiniMax-M2 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 2 | MiniMax-M2 |
|---|---|---|
| Provider | Anthropic | MiniMax |
| Noometry Index | 24.7 | 36.9 |
| Rank | 342 | 201 |
| Context | — | 205K |
| Input $/M | — | $0.30 |
| Output $/M | — | $1.20 |
| Weights | Proprietary | Open |

## Coding

- Claude 2: —
- MiniMax-M2: 39.1 (#151)

| Benchmark | Claude 2 | MiniMax-M2 |
|---|---|---|
| SWE-bench Verified (bash only) | — | 61% |
| LMArena WebDev | — | 1297 |
| LMArena Coding | — | 1370 |
| HumanEval+ | 61.6% | — |

## Agentic & Tool Use

- Claude 2: —
- MiniMax-M2: 24.9 (#102)

| Benchmark | Claude 2 | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| Vending-Bench 2 | — | 160.6 |

## Reasoning

- Claude 2: 20.8 (#213)
- MiniMax-M2: 18.6 (#256)

| Benchmark | Claude 2 | MiniMax-M2 |
|---|---|---|
| Kagi LLM Benchmark | — | 57.8% |
| NYT Connections (extended) | — | 14.8% |
| LMArena Hard Prompts | — | 1357 |
| DTBench | 51.9% | — |
| Epoch Capabilities Index | 120.08 | — |

## Math

- Claude 2: 8.7 (#314)
- MiniMax-M2: 34.6 (#158)

| Benchmark | Claude 2 | MiniMax-M2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| LMArena Math | — | 1350 |
| MATH Level 5 | 11.7% | — |

## Knowledge

- Claude 2: 17.0 (#282)
- MiniMax-M2: 36.3 (#160)

| Benchmark | Claude 2 | MiniMax-M2 |
|---|---|---|
| GPQA Diamond | 34.7% | — |
| LMArena Expert | — | 1336 |
| MMLU | 78.5% | — |
| TriviaQA | 87.5% | — |

## Multilingual

- Claude 2: —
- MiniMax-M2: 45.6 (#165)

| Benchmark | Claude 2 | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | — | 1314 |
| LMArena Chinese | — | 1367 |
| LMArena French | — | 1336 |
| LMArena German | — | 1366 |
| LMArena Russian | — | 1332 |
| LMArena Spanish | — | 1326 |

## Instruction Following

- Claude 2: —
- MiniMax-M2: 70.4 (#160)

| Benchmark | Claude 2 | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | — | 1329 |

## Long Context

- Claude 2: —
- MiniMax-M2: 40.5 (#148)

| Benchmark | Claude 2 | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | — | 1332 |

## Writing & Preference

- Claude 2: —
- MiniMax-M2: 53.3 (#157)

| Benchmark | Claude 2 | MiniMax-M2 |
|---|---|---|
| LMArena Text | — | 1340 |
| LMArena Creative Writing | — | 1288 |
| LMArena Multi-Turn | — | 1362 |

## FAQ

### Is Claude 2 better than MiniMax-M2?

MiniMax-M2 is the stronger model overall, scoring 36.9 to 24.7 on the Noometry Index.

### How many benchmarks do Claude 2 and MiniMax-M2 share?

0 benchmarks have published results for both models. Claude 2 has 8 scored results on Noometry and MiniMax-M2 has 21.