Model comparison
Claude Sonnet 4.5 vs Qwen3.8 27B
Qwen3.8 27B is the stronger model overall, scoring 46.0 to 44.1 on the Noometry Index.
Last verified . 28 shared benchmarks.
Alibaba (Qwen)Summary
- They share 28 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 4 categories and Qwen3.8 27B in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.8 27B leads 41.0 to 26.9.
- The biggest single-benchmark swing is ARC-AGI-2: 13.6% for Claude Sonnet 4.5 and 42.4% for Qwen3.8 27B.
- Qwen3.8 27B is cheaper at $0.04 / $2.30 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
- Qwen3.8 27B accepts more context: 262K tokens versus 200K.
- Qwen3.8 27B has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4.5 | Qwen3.8 27B | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 44.1 | 46.0 |
| Released | 2025-09-29 | 2026-08-14 |
| Weights | Proprietary | Open |
| Context window | 200K | 262K |
| Max output | 64K | 33K |
| Input $ / M tokens | $3 | $0.04 |
| Output $ / M tokens | $15 | $2.30 |
| Results tracked | 73 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 27B leads
Claude Sonnet 4.5: 47.3 (#61), Qwen3.8 27B: 50.5 (#44)
| Benchmark | Claude Sonnet 4.5 | Qwen3.8 27B |
|---|---|---|
| LMArena WebDev | 1393 | 1593 |
| SciCode | 44.7% | 46.6% |
| LMArena Coding | 1489 | 1482 |
| SWE-bench Verified | 71.3% | — |
| SWE-bench Verified (bash only) | 71.4% | — |
| SWE-bench Multilingual | 67% | — |
| GSO | 14.7% | — |
| WeirdML | 47.7% | — |
| ALE-Bench | 796.15 | — |
| AlgoTune | 1.52 | — |
Agentic & Tool Use Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 38.3 (#32), Qwen3.8 27B: 32.9 (#57)
| Benchmark | Claude Sonnet 4.5 | Qwen3.8 27B |
|---|---|---|
| Terminal-Bench | 46.5% | — |
| APEX-Agents | — | 47.5% |
| Berkeley Function Calling Leaderboard | 73.2% | — |
| GDPval | 42.5% | — |
| Remote Labor Index | 2.1% | — |
| τ²-bench Airline | 72% | — |
| τ²-bench Banking | 25.3% | — |
| τ²-bench Retail | 72.4% | — |
| τ²-bench Telecom | 84.9% | — |
| Cybench | 60% | — |
| DeepResearch Bench | 52.6% | — |
| OSWorld | 62.9% | — |
| LMArena Search | 1159 | — |
| METR Time Horizons | 67.4% | — |
| Vending-Bench 2 | 3,839 | — |
Reasoning Qwen3.8 27B leads
Claude Sonnet 4.5: 26.9 (#125), Qwen3.8 27B: 41.0 (#54)
| Benchmark | Claude Sonnet 4.5 | Qwen3.8 27B |
|---|---|---|
| ARC-AGI-2 | 13.6% | 42.4% |
| NYT Connections (extended) | 37.3% | 54.5% |
| ARC-AGI-1 | 63.7% | 87.5% |
| CritPt | 1.1% | 5.4% |
| LMArena Hard Prompts | 1462 | 1460 |
| DTBench | 83.2% | 88% |
| LMCA | 38.8% | 41.4% |
| Epoch Capabilities Index | 146.84 | 149.38 |
| SimpleBench | 54.3% | — |
| Kagi LLM Benchmark | 57.9% | — |
| Chess Puzzles | 12% | — |
| EnigmaEval | 6% | — |
| EBR-Bench | 2.4% | — |
| Mystery Game Puzzles | 17% | — |
| Surface Evolver Bench | — | 45% |
| ForecastBench | 61.9 | — |
Math Qwen3.8 27B leads
Claude Sonnet 4.5: 32.3 (#216), Qwen3.8 27B: 37.1 (#161)
| Benchmark | Claude Sonnet 4.5 | Qwen3.8 27B |
|---|---|---|
| ProofBench | 19% | 16% |
| LMArena Math | 1449 | 1456 |
| FrontierMath (Tiers 1-3) | 23.9% | — |
| FrontierMath Tier 4 | 2.4% | — |
| OTIS Mock AIME 2024-2025 | 77.8% | — |
| Omni-MATH | 55.3% | — |
| MATH Level 5 | 97.7% | — |
| FrontierMath (Feb 2025 set) | 15.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 48.4 (#76), Qwen3.8 27B: 41.6 (#109)
| Benchmark | Claude Sonnet 4.5 | Qwen3.8 27B |
|---|---|---|
| LMArena Expert | 1482 | 1482 |
| GPQA Diamond | 82.3% | — |
| Humanity's Last Exam | 13.7% | — |
| SimpleQA Verified | 30.7% | — |
| MMLU-Pro | 86.9% | — |
| Vectara Hallucination Rate | 12% | — |
| GPQA (HELM) | 68.6% | — |
Multimodal Qwen3.8 27B leads
Claude Sonnet 4.5: 34.8 (#89), Qwen3.8 27B: 41.3 (#37)
| Benchmark | Claude Sonnet 4.5 | Qwen3.8 27B |
|---|---|---|
| LMArena Vision | — | 1271 |
| VPCT | 39.8% | — |
| LMArena Document | 1450 | — |
Multilingual Too close to call
Claude Sonnet 4.5: 53.4 (#69), Qwen3.8 27B: 53.7 (#60)
| Benchmark | Claude Sonnet 4.5 | Qwen3.8 27B |
|---|---|---|
| LMArena Non-English | 1425 | 1430 |
| LMArena Chinese | 1459 | 1504 |
| LMArena French | 1458 | 1465 |
| LMArena German | 1427 | 1438 |
| LMArena Japanese | 1390 | 1384 |
| LMArena Korean | 1403 | 1393 |
| LMArena Russian | 1437 | 1415 |
| LMArena Spanish | 1457 | 1448 |
Instruction Following Too close to call
Claude Sonnet 4.5: 75.0 (#78), Qwen3.8 27B: 75.8 (#53)
| Benchmark | Claude Sonnet 4.5 | Qwen3.8 27B |
|---|---|---|
| LMArena Instruction Following | 1459 | 1439 |
| IFEval | 85% | — |
Long Context Too close to call
Claude Sonnet 4.5: 45.2 (#46), Qwen3.8 27B: 44.3 (#70)
| Benchmark | Claude Sonnet 4.5 | Qwen3.8 27B |
|---|---|---|
| LMArena Longer Query | 1476 | 1450 |
Writing & Preference Too close to call
Claude Sonnet 4.5: 66.5 (#34), Qwen3.8 27B: 65.8 (#43)
| Benchmark | Claude Sonnet 4.5 | Qwen3.8 27B |
|---|---|---|
| LMArena Text | 1439 | 1441 |
| LMArena Creative Writing | 1442 | 1384 |
| EQ-Bench Creative Writing | 1678 | 1671 |
| LMArena Multi-Turn | 1465 | 1441 |
| WildBench | 85.4% | — |
Frequently asked questions
Is Claude Sonnet 4.5 better than Qwen3.8 27B?
Qwen3.8 27B is the stronger model overall, scoring 46.0 to 44.1 on the Noometry Index.
Which is cheaper, Claude Sonnet 4.5 or Qwen3.8 27B?
Qwen3.8 27B is cheaper. It lists at $0.04 per million input tokens and $2.30 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.
Is Claude Sonnet 4.5 or Qwen3.8 27B better for coding?
Qwen3.8 27B scores higher on coding benchmarks: 50.5 versus 47.3 in the Noometry coding category.
Which has the bigger context window?
Qwen3.8 27B does, with 262K tokens against 200K.
How many benchmarks do Claude Sonnet 4.5 and Qwen3.8 27B share?
28 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Qwen3.8 27B has 31.