# Claude Sonnet 4.6 vs Qwen Max

> Claude Sonnet 4.6 is the stronger model overall, scoring 50.1 to 34.4 on the Noometry Index. Qwen Max costs 2.1× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-sonnet-4-6-vs-qwen-max
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 8 categories and Qwen Max in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 4.6 leads 51.9 to 21.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 85.8% for Claude Sonnet 4.6 and 16.1% for Qwen Max.
- Qwen Max is cheaper at $1.60 / $6.40 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.6.
- Claude Sonnet 4.6 accepts more context: 1M tokens versus 33K.

## Snapshot

| | Claude Sonnet 4.6 | Qwen Max |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 50.1 | 34.4 |
| Rank | 42 | 226 |
| Context | 1M | 33K |
| Input $/M | $3 | $1.60 |
| Output $/M | $15 | $6.40 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Sonnet 4.6: 46.0 (#62)
- Qwen Max: 30.3 (#288)

| Benchmark | Claude Sonnet 4.6 | Qwen Max |
|---|---|---|
| LMArena Coding | 1504 | 1288 |
| SWE-bench Verified | 75.2% | — |
| DeepSWE | 29.9% | — |
| FrontierCode | 24.3% | — |
| Aider Polyglot | — | 21.8% |
| LMArena WebDev | 1521 | — |
| SciCode | 46.8% | — |
| WeirdML | 66.1% | — |
| ALE-Bench | 1,327 | — |

## Agentic & Tool Use

- Claude Sonnet 4.6: 39.1 (#26)
- Qwen Max: —

| Benchmark | Claude Sonnet 4.6 | Qwen Max |
|---|---|---|
| Terminal-Bench | 53.4% | — |
| APEX-Agents | 43% | — |
| OSWorld 2.0 | 9.3% | — |
| DeepResearch Bench | 54.9% | — |
| OSWorld | 72.1% | — |
| ExploitBench | 23.6% | — |
| GBAEval | 48.8% | — |
| GDP.pdf | 18% | — |
| LMArena Search | 1221 | — |
| Vending-Bench 2 | 7,204 | — |

## Reasoning

- Claude Sonnet 4.6: 46.1 (#40)
- Qwen Max: 24.1 (#154)

| Benchmark | Claude Sonnet 4.6 | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1485 | 1270 |
| ARC-AGI-2 | 60.4% | — |
| NYT Connections (extended) | 80.9% | — |
| ARC-AGI-1 | 86.5% | — |
| CritPt | 3.1% | — |
| Chess Puzzles | 13% | — |
| Thematic Generalization | 76.3% | — |
| Mystery Game Puzzles | 16% | — |
| DTBench | 89.9% | — |
| LMCA | 46.5% | — |
| Epoch Capabilities Index | 152.25 | — |
| ForecastBench | 62 | — |

## Math

- Claude Sonnet 4.6: 51.9 (#41)
- Qwen Max: 21.0 (#272)

| Benchmark | Claude Sonnet 4.6 | Qwen Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 85.8% | 16.1% |
| LMArena Math | 1463 | 1275 |
| FrontierMath (Feb 2025 set) | 32.4% | 1% |
| ProofBench | 45% | — |
| MATH Level 5 | — | 67.2% |
| FrontierMath Tier 4 (v1) | 8.3% | — |

## Knowledge

- Claude Sonnet 4.6: 51.6 (#60)
- Qwen Max: 30.3 (#222)

| Benchmark | Claude Sonnet 4.6 | Qwen Max |
|---|---|---|
| GPQA Diamond | 87.4% | 56.1% |
| LMArena Expert | 1500 | 1248 |
| SimpleQA Verified | 35.5% | — |
| Vectara Hallucination Rate | 10.6% | — |

## Multimodal

- Claude Sonnet 4.6: 38.0 (#61)
- Qwen Max: —

| Benchmark | Claude Sonnet 4.6 | Qwen Max |
|---|---|---|
| LMArena Vision | 1283 | — |
| Blueprint-Bench 2 | 6.7% | — |
| LMArena Document | 1482 | — |

## Multilingual

- Claude Sonnet 4.6: 54.6 (#39)
- Qwen Max: 42.0 (#197)

| Benchmark | Claude Sonnet 4.6 | Qwen Max |
|---|---|---|
| LMArena Non-English | 1440 | 1263 |
| LMArena Chinese | 1491 | 1254 |
| LMArena French | 1465 | 1329 |
| LMArena German | 1428 | 1254 |
| LMArena Japanese | 1419 | 1205 |
| LMArena Korean | 1411 | 1141 |
| LMArena Russian | 1440 | 1274 |
| LMArena Spanish | 1465 | 1290 |

## Instruction Following

- Claude Sonnet 4.6: 77.6 (#23)
- Qwen Max: 66.7 (#203)

| Benchmark | Claude Sonnet 4.6 | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1476 | 1262 |

## Long Context

- Claude Sonnet 4.6: 45.3 (#40)
- Qwen Max: 39.4 (#175)

| Benchmark | Claude Sonnet 4.6 | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1479 | 1289 |
| Fiction.LiveBench | — | 66.7% |

## Writing & Preference

- Claude Sonnet 4.6: 70.4 (#22)
- Qwen Max: 48.0 (#200)

| Benchmark | Claude Sonnet 4.6 | Qwen Max |
|---|---|---|
| LMArena Text | 1458 | 1282 |
| LMArena Creative Writing | 1435 | 1248 |
| LMArena Multi-Turn | 1464 | 1277 |
| EQ-Bench Creative Writing | 1810 | — |
| EQ-Bench 4 | 1207 | — |

## FAQ

### Is Claude Sonnet 4.6 better than Qwen Max?

Claude Sonnet 4.6 is the stronger model overall, scoring 50.1 to 34.4 on the Noometry Index. Qwen Max costs 2.1× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.

### Which is cheaper, Claude Sonnet 4.6 or Qwen Max?

Qwen Max is cheaper. It lists at $1.60 per million input tokens and $6.40 per million output tokens; Claude Sonnet 4.6 lists at $3 and $15.

### Is Claude Sonnet 4.6 or Qwen Max better for coding?

Claude Sonnet 4.6 scores higher on coding benchmarks: 46.0 versus 30.3 in the Noometry coding category.

### Which has the bigger context window?

Claude Sonnet 4.6 does, with 1M tokens against 33K.

### How many benchmarks do Claude Sonnet 4.6 and Qwen Max share?

20 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Qwen Max has 23.