# Claude 2.1 vs Qwen2-72B

> Qwen2-72B is the stronger model overall, scoring 30.0 to 25.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-2-1-vs-qwen2-72b
- Last updated: 2026-10-12
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Claude 2.1 scores higher in 0 categories and Qwen2-72B in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2-72B leads 30.2 to 10.2.
- The biggest single-benchmark swing is GPQA Diamond: 33% for Claude 2.1 and 40.8% for Qwen2-72B.
- Qwen2-72B has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 2.1 | Qwen2-72B |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 25.2 | 30.0 |
| Rank | 345 | 300 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Claude 2.1: 26.2 (#327)
- Qwen2-72B: 29.1 (#310)

| Benchmark | Claude 2.1 | Qwen2-72B |
|---|---|---|
| WeirdML | 7.1% | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| LMArena Coding | — | 1196 |
| BigCodeBench Complete | — | 54% |

## Agentic & Tool Use

- Claude 2.1: —
- Qwen2-72B: 17.0 (#146)

| Benchmark | Claude 2.1 | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |

## Reasoning

- Claude 2.1: 21.4 (#221)
- Qwen2-72B: 23.2 (#181)

| Benchmark | Claude 2.1 | Qwen2-72B |
|---|---|---|
| Epoch Capabilities Index | 119.27 | 125.28 |
| LMArena Hard Prompts | — | 1191 |
| DTBench | 51% | — |
| ForecastBench | 54.2 | — |

## Math

- Claude 2.1: 10.2 (#315)
- Qwen2-72B: 30.2 (#236)

| Benchmark | Claude 2.1 | Qwen2-72B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| LMArena Math | — | 1235 |
| MATH Level 5 | — | 39.1% |

## Knowledge

- Claude 2.1: 15.4 (#292)
- Qwen2-72B: 21.2 (#275)

| Benchmark | Claude 2.1 | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 33% | 40.8% |
| MMLU | 73.5% | 82.4% |
| LMArena Expert | — | 1171 |

## Multilingual

- Claude 2.1: —
- Qwen2-72B: 35.9 (#244)

| Benchmark | Claude 2.1 | Qwen2-72B |
|---|---|---|
| LMArena Non-English | — | 1176 |
| LMArena Chinese | — | 1240 |
| LMArena French | — | 1170 |
| LMArena German | — | 1151 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |
| LMArena Russian | — | 1169 |
| LMArena Spanish | — | 1169 |

## Instruction Following

- Claude 2.1: —
- Qwen2-72B: 61.7 (#241)

| Benchmark | Claude 2.1 | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | — | 1181 |

## Long Context

- Claude 2.1: —
- Qwen2-72B: 36.1 (#235)

| Benchmark | Claude 2.1 | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | — | 1192 |

## Writing & Preference

- Claude 2.1: —
- Qwen2-72B: 40.8 (#241)

| Benchmark | Claude 2.1 | Qwen2-72B |
|---|---|---|
| LMArena Text | — | 1203 |
| LMArena Creative Writing | — | 1181 |
| LMArena Multi-Turn | — | 1196 |

## FAQ

### Is Claude 2.1 better than Qwen2-72B?

Qwen2-72B is the stronger model overall, scoring 30.0 to 25.2 on the Noometry Index.

### Is Claude 2.1 or Qwen2-72B better for coding?

Qwen2-72B scores higher on coding benchmarks: 29.1 versus 26.2 in the Noometry coding category.

### How many benchmarks do Claude 2.1 and Qwen2-72B share?

4 benchmarks have published results for both models. Claude 2.1 has 7 scored results on Noometry and Qwen2-72B has 26.