# Claude 2.1 vs MiniMax-M2.7

> MiniMax-M2.7 is the stronger model overall, scoring 37.4 to 24.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-2-1-vs-minimax-m2-7
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. Claude 2.1 scores higher in 1 category and MiniMax-M2.7 in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M2.7 leads 37.1 to 15.5.
- The biggest single-benchmark swing is WeirdML: 7.1% for Claude 2.1 and 37% for MiniMax-M2.7.
- MiniMax-M2.7 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 2.1 | MiniMax-M2.7 |
|---|---|---|
| Provider | Anthropic | MiniMax |
| Noometry Index | 24.9 | 37.4 |
| Rank | 340 | 188 |
| Context | — | 205K |
| Input $/M | — | $0.30 |
| Output $/M | — | $1.20 |
| Weights | Proprietary | Open |

## Coding

- Claude 2.1: 25.8 (#322)
- MiniMax-M2.7: 41.4 (#115)

| Benchmark | Claude 2.1 | MiniMax-M2.7 |
|---|---|---|
| WeirdML | 7.1% | 37% |
| LMArena WebDev | — | 1397 |
| SciCode | — | 47% |
| LMArena Coding | — | 1454 |
| ALE-Bench | — | 599.25 |

## Agentic & Tool Use

- Claude 2.1: —
- MiniMax-M2.7: 24.9 (#103)

| Benchmark | Claude 2.1 | MiniMax-M2.7 |
|---|---|---|
| Terminal-Bench | — | 45.1% |
| ExploitBench | — | 13.3% |
| GBAEval | — | 0% |

## Reasoning

- Claude 2.1: 20.6 (#216)
- MiniMax-M2.7: 19.0 (#248)

| Benchmark | Claude 2.1 | MiniMax-M2.7 |
|---|---|---|
| Epoch Capabilities Index | 119.22 | 145.84 |
| NYT Connections (extended) | — | 24.7% |
| CritPt | — | 0.6% |
| Thematic Generalization | — | 39.3% |
| LMArena Hard Prompts | — | 1422 |
| DTBench | 51% | — |
| ForecastBench | 54.2 | — |

## Math

- Claude 2.1: 9.6 (#309)
- MiniMax-M2.7: 24.9 (#254)

| Benchmark | Claude 2.1 | MiniMax-M2.7 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| ProofBench | — | 3% |
| LMArena Math | — | 1420 |

## Knowledge

- Claude 2.1: 15.5 (#287)
- MiniMax-M2.7: 37.1 (#151)

| Benchmark | Claude 2.1 | MiniMax-M2.7 |
|---|---|---|
| GPQA Diamond | 33% | — |
| Vectara Hallucination Rate | — | 12.9% |
| LMArena Expert | — | 1443 |
| MMLU | 73.5% | — |

## Multilingual

- Claude 2.1: —
- MiniMax-M2.7: 50.5 (#120)

| Benchmark | Claude 2.1 | MiniMax-M2.7 |
|---|---|---|
| LMArena Non-English | — | 1382 |
| LMArena Chinese | — | 1439 |
| LMArena French | — | 1422 |
| LMArena German | — | 1398 |
| LMArena Japanese | — | 1261 |
| LMArena Korean | — | 1313 |
| LMArena Russian | — | 1383 |
| LMArena Spanish | — | 1403 |

## Instruction Following

- Claude 2.1: —
- MiniMax-M2.7: 74.2 (#101)

| Benchmark | Claude 2.1 | MiniMax-M2.7 |
|---|---|---|
| LMArena Instruction Following | — | 1404 |

## Long Context

- Claude 2.1: —
- MiniMax-M2.7: 43.3 (#94)

| Benchmark | Claude 2.1 | MiniMax-M2.7 |
|---|---|---|
| LMArena Longer Query | — | 1419 |

## Writing & Preference

- Claude 2.1: —
- MiniMax-M2.7: 59.1 (#107)

| Benchmark | Claude 2.1 | MiniMax-M2.7 |
|---|---|---|
| LMArena Text | — | 1404 |
| LMArena Creative Writing | — | 1354 |
| LMArena Multi-Turn | — | 1413 |

## FAQ

### Is Claude 2.1 better than MiniMax-M2.7?

MiniMax-M2.7 is the stronger model overall, scoring 37.4 to 24.9 on the Noometry Index.

### Is Claude 2.1 or MiniMax-M2.7 better for coding?

MiniMax-M2.7 scores higher on coding benchmarks: 41.4 versus 25.8 in the Noometry coding category.

### How many benchmarks do Claude 2.1 and MiniMax-M2.7 share?

2 benchmarks have published results for both models. Claude 2.1 has 7 scored results on Noometry and MiniMax-M2.7 has 30.