# Claude Sonnet 4 vs Qwen3.8 Max

> Qwen3.8 Max is the stronger model overall, scoring 56.0 to 40.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-sonnet-4-vs-qwen3-8-max
- Last updated: 2026-10-10
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. Claude Sonnet 4 scores higher in 0 categories and Qwen3.8 Max in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.1 to 41.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 71.1% for Claude Sonnet 4 and 100% for Qwen3.8 Max.
- Qwen3.8 Max is cheaper at $2 / $6 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
- Qwen3.8 Max accepts more context: 1M tokens versus 200K.

## Snapshot

| | Claude Sonnet 4 | Qwen3.8 Max |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 40.6 | 56.0 |
| Rank | 139 | 21 |
| Context | 200K | 1M |
| Input $/M | $3 | $2 |
| Output $/M | $15 | $6 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Sonnet 4: 44.0 (#70)
- Qwen3.8 Max: 52.3 (#30)

| Benchmark | Claude Sonnet 4 | Qwen3.8 Max |
|---|---|---|
| SciCode | 40% | 52.9% |
| LMArena Coding | 1414 | 1499 |
| DeepSWE | — | 57.5% |
| SWE-bench Verified (bash only) | 64.9% | — |
| Aider Polyglot | 61.3% | — |
| LMArena WebDev | — | 1671 |
| FrontierSWE | — | 15.8% |
| GSO | 4.9% | — |
| WeirdML | 46.1% | — |
| ALE-Bench | 655.35 | — |

## Agentic & Tool Use

- Claude Sonnet 4: 38.3 (#29)
- Qwen3.8 Max: 42.6 (#17)

| Benchmark | Claude Sonnet 4 | Qwen3.8 Max |
|---|---|---|
| TheAgentCompany | 33.1% | — |
| τ²-bench Banking | — | 55.1% |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| GDP.pdf | — | 23.2% |
| METR Time Horizons | 62% | — |

## Reasoning

- Claude Sonnet 4: 23.0 (#169)
- Qwen3.8 Max: 53.4 (#26)

| Benchmark | Claude Sonnet 4 | Qwen3.8 Max |
|---|---|---|
| CritPt | 0.3% | 20% |
| LMArena Hard Prompts | 1372 | 1493 |
| DTBench | 77.1% | 92% |
| LMCA | 29% | 46.2% |
| Epoch Capabilities Index | 141.69 | 156.69 |
| ARC-AGI-2 | 5.9% | — |
| SimpleBench | 45.5% | — |
| Kagi LLM Benchmark | 73% | — |
| NYT Connections (extended) | — | 88.3% |
| ARC-AGI-1 | 40% | — |
| Chess Puzzles | — | 40% |
| EnigmaEval | 3.1% | — |
| Mystery Game Puzzles | — | 38% |
| ForecastBench | 60.2 | — |

## Math

- Claude Sonnet 4: 41.5 (#71)
- Qwen3.8 Max: 73.1 (#15)

| Benchmark | Claude Sonnet 4 | Qwen3.8 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 100% |
| LMArena Math | 1375 | 1498 |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| ProofBench | — | 58% |
| Omni-MATH | 60.2% | — |
| MATH Level 5 | 84.4% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |

## Knowledge

- Claude Sonnet 4: 41.6 (#99)
- Qwen3.8 Max: 61.7 (#25)

| Benchmark | Claude Sonnet 4 | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | 79.2% | 92.7% |
| LMArena Expert | 1371 | 1504 |
| Humanity's Last Exam | 7.8% | — |
| SimpleQA Verified | — | 47.3% |
| MMLU-Pro | 84.3% | — |
| Confabulations | 13.2% | — |
| Vectara Hallucination Rate | 10.3% | — |
| GPQA (HELM) | 70.6% | — |

## Multimodal

- Claude Sonnet 4: 25.6 (#116)
- Qwen3.8 Max: 36.9 (#70)

| Benchmark | Claude Sonnet 4 | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | 1191 | 1314 |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| Furniture Assembly | — | 20% |
| MindCube | 44.8% | — |

## Multilingual

- Claude Sonnet 4: 46.9 (#151)
- Qwen3.8 Max: 56.6 (#18)

| Benchmark | Claude Sonnet 4 | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1333 | 1468 |
| LMArena Chinese | 1351 | 1537 |
| LMArena French | 1364 | 1502 |
| LMArena German | 1331 | 1489 |
| LMArena Japanese | 1301 | 1466 |
| LMArena Korean | 1293 | 1467 |
| LMArena Russian | 1355 | 1478 |
| LMArena Spanish | 1356 | 1495 |

## Instruction Following

- Claude Sonnet 4: 71.8 (#141)
- Qwen3.8 Max: 77.7 (#19)

| Benchmark | Claude Sonnet 4 | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1375 | 1478 |
| IFEval | 84% | — |

## Long Context

- Claude Sonnet 4: 33.6 (#254)
- Qwen3.8 Max: 45.5 (#30)

| Benchmark | Claude Sonnet 4 | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1398 | 1486 |
| Fiction.LiveBench | 46.9% | — |

## Writing & Preference

- Claude Sonnet 4: 57.3 (#127)
- Qwen3.8 Max: 67.0 (#31)

| Benchmark | Claude Sonnet 4 | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1351 | 1480 |
| LMArena Creative Writing | 1345 | 1478 |
| LMArena Multi-Turn | 1376 | 1487 |
| Short-Story Creative Writing | 81.4% | — |
| EQ-Bench Creative Writing | 1483 | — |
| WildBench | 83.8% | — |

## FAQ

### Is Claude Sonnet 4 better than Qwen3.8 Max?

Qwen3.8 Max is the stronger model overall, scoring 56.0 to 40.6 on the Noometry Index.

### Which is cheaper, Claude Sonnet 4 or Qwen3.8 Max?

Qwen3.8 Max is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; Claude Sonnet 4 lists at $3 and $15.

### Is Claude Sonnet 4 or Qwen3.8 Max better for coding?

Qwen3.8 Max scores higher on coding benchmarks: 52.3 versus 44.0 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.8 Max does, with 1M tokens against 200K.

### How many benchmarks do Claude Sonnet 4 and Qwen3.8 Max share?

25 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Qwen3.8 Max has 38.