# Claude Sonnet 5 vs Qwen3 235B-A22B

> Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 43.5 on the Noometry Index. Qwen3 235B-A22B costs 3.3× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-sonnet-5-vs-qwen3-235b-a22b
- Last updated: 2026-10-10
- Shared benchmarks: 32

## Summary

- They share 32 benchmarks with published results for both. Claude Sonnet 5 scores higher in 8 categories and Qwen3 235B-A22B in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Sonnet 5 leads 49.1 to 15.7.
- The biggest single-benchmark swing is SimpleBench: 60.6% for Claude Sonnet 5 and 31% for Qwen3 235B-A22B.
- Qwen3 235B-A22B is cheaper at $0.70 / $2.80 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.
- Claude Sonnet 5 accepts more context: 1M tokens versus 131K.
- Qwen3 235B-A22B has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Sonnet 5 | Qwen3 235B-A22B |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 54.6 | 43.5 |
| Rank | 29 | 91 |
| Context | 1M | 131K |
| Input $/M | $2 | $0.70 |
| Output $/M | $10 | $2.80 |
| Weights | Proprietary | Open |

## Coding

- Claude Sonnet 5: 55.5 (#26)
- Qwen3 235B-A22B: 44.3 (#75)

| Benchmark | Claude Sonnet 5 | Qwen3 235B-A22B |
|---|---|---|
| SciCode | 54.3% | 42.4% |
| WeirdML | 68.8% | 41% |
| LMArena Coding | 1483 | 1445 |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.7% | — |
| Aider Polyglot | — | 59.6% |
| CursorBench | 34.1% | — |
| LMArena WebDev | 1541 | — |
| GSO | 37.3% | — |
| ALE-Bench | 1,463 | — |

## Agentic & Tool Use

- Claude Sonnet 5: 42.8 (#18)
- Qwen3 235B-A22B: 33.9 (#51)

| Benchmark | Claude Sonnet 5 | Qwen3 235B-A22B |
|---|---|---|
| Vending-Bench 2 | 6,378 | -11.34 |
| APEX-Agents | 54.5% | — |
| Berkeley Function Calling Leaderboard | — | 52.1% |
| GBAEval | 65.3% | — |
| LMArena Search | 1194 | — |

## Reasoning

- Claude Sonnet 5: 49.1 (#39)
- Qwen3 235B-A22B: 15.7 (#311)

| Benchmark | Claude Sonnet 5 | Qwen3 235B-A22B |
|---|---|---|
| SimpleBench | 60.6% | 31% |
| CritPt | 16.9% | 0% |
| Chess Puzzles | 35% | 12% |
| LMArena Hard Prompts | 1461 | 1433 |
| Mystery Game Puzzles | 35% | 9% |
| DTBench | 92.5% | 80.3% |
| LMCA | 50% | 29.3% |
| Epoch Capabilities Index | 156.21 | 143.85 |
| ForecastBench | 61.1 | 59.7 |
| ARC-AGI-2 | — | 1.3% |
| Kagi LLM Benchmark | — | 69.4% |
| NYT Connections (extended) | 75.1% | — |
| ARC-AGI-1 | — | 11% |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |

## Math

- Claude Sonnet 5: 66.2 (#27)
- Qwen3 235B-A22B: 50.4 (#57)

| Benchmark | Claude Sonnet 5 | Qwen3 235B-A22B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 94.7% | 86.7% |
| LMArena Math | 1467 | 1432 |
| FrontierMath (Tiers 1-3) | 65.6% | — |
| FrontierMath Tier 4 | 29.3% | — |
| ProofBench | 77% | — |
| Omni-MATH | — | 71.8% |
| MATH Level 5 | — | 68.9% |
| FrontierMath (Feb 2025 set) | — | 8.5% |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- Claude Sonnet 5: 55.6 (#47)
- Qwen3 235B-A22B: 49.6 (#73)

| Benchmark | Claude Sonnet 5 | Qwen3 235B-A22B |
|---|---|---|
| GPQA Diamond | 90.5% | 80.1% |
| SimpleQA Verified | 33.7% | 40.4% |
| LMArena Expert | 1490 | 1463 |
| MMLU-Pro | — | 84.4% |
| Confabulations | — | 15.6% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 72.7% |

## Multimodal

- Claude Sonnet 5: 42.4 (#31)
- Qwen3 235B-A22B: —

| Benchmark | Claude Sonnet 5 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Vision | 1274 | — |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |

## Multilingual

- Claude Sonnet 5: 53.8 (#55)
- Qwen3 235B-A22B: 52.3 (#89)

| Benchmark | Claude Sonnet 5 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1431 | 1409 |
| LMArena Chinese | 1477 | 1481 |
| LMArena French | 1460 | 1445 |
| LMArena German | 1440 | 1433 |
| LMArena Japanese | 1422 | 1399 |
| LMArena Korean | 1411 | 1391 |
| LMArena Russian | 1451 | 1411 |
| LMArena Spanish | 1437 | 1430 |

## Instruction Following

- Claude Sonnet 5: 76.3 (#41)
- Qwen3 235B-A22B: 72.6 (#136)

| Benchmark | Claude Sonnet 5 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Instruction Following | 1452 | 1408 |
| IFEval | — | 83.5% |

## Long Context

- Claude Sonnet 5: 44.8 (#55)
- Qwen3 235B-A22B: 46.1 (#26)

| Benchmark | Claude Sonnet 5 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1463 | 1426 |
| Fiction.LiveBench | — | 75% |

## Writing & Preference

- Claude Sonnet 5: 69.2 (#25)
- Qwen3 235B-A22B: 59.6 (#108)

| Benchmark | Claude Sonnet 5 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1442 | 1419 |
| LMArena Creative Writing | 1416 | 1384 |
| EQ-Bench Creative Writing | 1794 | 1366 |
| LMArena Multi-Turn | 1454 | 1432 |
| Short-Story Creative Writing | — | 83% |
| WildBench | — | 86.6% |
| EQ-Bench 4 | 1236 | — |

## FAQ

### Is Claude Sonnet 5 better than Qwen3 235B-A22B?

Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 43.5 on the Noometry Index. Qwen3 235B-A22B costs 3.3× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.

### Which is cheaper, Claude Sonnet 5 or Qwen3 235B-A22B?

Qwen3 235B-A22B is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; Claude Sonnet 5 lists at $2 and $10.

### Is Claude Sonnet 5 or Qwen3 235B-A22B better for coding?

Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 44.3 in the Noometry coding category.

### Which has the bigger context window?

Claude Sonnet 5 does, with 1M tokens against 131K.

### How many benchmarks do Claude Sonnet 5 and Qwen3 235B-A22B share?

32 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and Qwen3 235B-A22B has 49.