Model comparison
Claude Sonnet 4.6 vs Qwen3.7 Plus
Claude Sonnet 4.6 is the stronger model overall, scoring 50.1 to 45.0 on the Noometry Index. Qwen3.7 Plus costs 8.6× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.
Last verified . 31 shared benchmarks.
Alibaba (Qwen)Summary
- They share 31 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 7 categories and Qwen3.7 Plus in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Claude Sonnet 4.6 leads 39.1 to 21.2.
- The biggest single-benchmark swing is FrontierCode: 24.3% for Claude Sonnet 4.6 and 10.2% for Qwen3.7 Plus.
- Qwen3.7 Plus is cheaper at $0.40 / $1.60 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.6.
Side by side
| Claude Sonnet 4.6 | Qwen3.7 Plus | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 50.1 | 45.0 |
| Released | 2026-02-17 | 2026-06-02 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1M |
| Max output | 128K | 131K |
| Input $ / M tokens | $3 | $0.40 |
| Output $ / M tokens | $15 | $1.60 |
| Results tracked | 57 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 46.0 (#62), Qwen3.7 Plus: 36.1 (#200)
| Benchmark | Claude Sonnet 4.6 | Qwen3.7 Plus |
|---|---|---|
| FrontierCode | 24.3% | 10.2% |
| SciCode | 46.8% | 45.5% |
| LMArena Coding | 1504 | 1473 |
| SWE-bench Verified | 75.2% | — |
| DeepSWE | 29.9% | — |
| LMArena WebDev | 1521 | — |
| WeirdML | 66.1% | — |
| ALE-Bench | 1,327 | — |
Agentic & Tool Use Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 39.1 (#26), Qwen3.7 Plus: 21.2 (#130)
| Benchmark | Claude Sonnet 4.6 | Qwen3.7 Plus |
|---|---|---|
| OSWorld 2.0 | 9.3% | 2.8% |
| Terminal-Bench | 53.4% | — |
| APEX-Agents | 43% | — |
| 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 leads
Claude Sonnet 4.6: 46.1 (#40), Qwen3.7 Plus: 38.4 (#54)
| Benchmark | Claude Sonnet 4.6 | Qwen3.7 Plus |
|---|---|---|
| NYT Connections (extended) | 80.9% | 74.8% |
| CritPt | 3.1% | 9.1% |
| Chess Puzzles | 13% | 24% |
| LMArena Hard Prompts | 1485 | 1460 |
| Mystery Game Puzzles | 16% | 17% |
| DTBench | 89.9% | 84% |
| LMCA | 46.5% | 37.6% |
| Epoch Capabilities Index | 152.25 | 147.39 |
| ARC-AGI-2 | 60.4% | — |
| ARC-AGI-1 | 86.5% | — |
| Thematic Generalization | 76.3% | — |
| ForecastBench | 62 | — |
Math Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 51.9 (#41), Qwen3.7 Plus: 49.3 (#47)
| Benchmark | Claude Sonnet 4.6 | Qwen3.7 Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 85.8% | 93.3% |
| LMArena Math | 1463 | 1467 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| ProofBench | 45% | — |
| FrontierMath (Feb 2025 set) | 32.4% | — |
| FrontierMath Tier 4 (v1) | 8.3% | — |
Knowledge Qwen3.7 Plus leads
Claude Sonnet 4.6: 51.6 (#60), Qwen3.7 Plus: 54.9 (#46)
| Benchmark | Claude Sonnet 4.6 | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 87.4% | 87.9% |
| LMArena Expert | 1500 | 1467 |
| SimpleQA Verified | 35.5% | — |
| Vectara Hallucination Rate | 10.6% | — |
Multimodal Qwen3.7 Plus leads
Claude Sonnet 4.6: 38.0 (#61), Qwen3.7 Plus: 41.2 (#30)
| Benchmark | Claude Sonnet 4.6 | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | 1283 | 1281 |
| LMArena Document | 1482 | 1444 |
| Blueprint-Bench 2 | 6.7% | — |
Multilingual Too close to call
Claude Sonnet 4.6: 54.6 (#39), Qwen3.7 Plus: 55.0 (#36)
| Benchmark | Claude Sonnet 4.6 | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1440 | 1445 |
| LMArena Chinese | 1491 | 1510 |
| LMArena French | 1465 | 1471 |
| LMArena German | 1428 | 1471 |
| LMArena Japanese | 1419 | 1411 |
| LMArena Korean | 1411 | 1416 |
| LMArena Russian | 1440 | 1457 |
| LMArena Spanish | 1465 | 1453 |
Instruction Following Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 77.6 (#23), Qwen3.7 Plus: 75.9 (#49)
| Benchmark | Claude Sonnet 4.6 | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1476 | 1439 |
Long Context Too close to call
Claude Sonnet 4.6: 45.3 (#40), Qwen3.7 Plus: 44.5 (#61)
| Benchmark | Claude Sonnet 4.6 | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1479 | 1454 |
Writing & Preference Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 70.4 (#22), Qwen3.7 Plus: 64.5 (#54)
| Benchmark | Claude Sonnet 4.6 | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1458 | 1454 |
| LMArena Creative Writing | 1435 | 1439 |
| LMArena Multi-Turn | 1464 | 1459 |
| EQ-Bench Creative Writing | 1810 | — |
| EQ-Bench 4 | 1207 | — |
Frequently asked questions
Is Claude Sonnet 4.6 better than Qwen3.7 Plus?
Claude Sonnet 4.6 is the stronger model overall, scoring 50.1 to 45.0 on the Noometry Index. Qwen3.7 Plus costs 8.6× 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 Qwen3.7 Plus?
Qwen3.7 Plus is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; Claude Sonnet 4.6 lists at $3 and $15.
Is Claude Sonnet 4.6 or Qwen3.7 Plus better for coding?
Claude Sonnet 4.6 scores higher on coding benchmarks: 46.0 versus 36.1 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do Claude Sonnet 4.6 and Qwen3.7 Plus share?
31 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Qwen3.7 Plus has 32.