Model comparison
Claude Opus 5.5 vs Qwen3 235B-A22B
Claude Opus 5.5 is the stronger model overall, scoring 68.6 to 43.5 on the Noometry Index. Qwen3 235B-A22B costs 6.5× less per token, which makes it the better buy when Claude Opus 5.5's lead doesn't matter for your workload.
Last verified . 27 shared benchmarks.
Alibaba (Qwen)Summary
- They share 27 benchmarks with published results for both. Claude Opus 5.5 scores higher in 9 categories and Qwen3 235B-A22B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Opus 5.5 leads 80.2 to 15.7.
- The biggest single-benchmark swing is ARC-AGI-2: 93.3% for Claude Opus 5.5 and 1.3% for Qwen3 235B-A22B.
- Qwen3 235B-A22B is cheaper at $0.70 / $2.80 per million input/output tokens, against $4 / $20 for Claude Opus 5.5.
- Claude Opus 5.5 accepts more context: 1M tokens versus 131K.
- Qwen3 235B-A22B has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 5.5 | Qwen3 235B-A22B | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 68.6 | 43.5 |
| Released | 2026-09-22 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | 1M | 131K |
| Max output | 128K | 16K |
| Input $ / M tokens | $4 | $0.70 |
| Output $ / M tokens | $20 | $2.80 |
| Results tracked | 44 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 5.5 leads
Claude Opus 5.5: 71.9 (#3), Qwen3 235B-A22B: 44.3 (#75)
| Benchmark | Claude Opus 5.5 | Qwen3 235B-A22B |
|---|---|---|
| SciCode | 66.9% | 42.4% |
| LMArena Coding | 1547 | 1445 |
| FrontierCode | 54.6% | — |
| Aider Polyglot | — | 59.6% |
| CursorBench | 57.8% | — |
| LMArena WebDev | 1813 | — |
| FrontierSWE | 62.3% | — |
| WeirdML | — | 41% |
| MirrorCode | 77.4% | — |
| ALE-Bench | 2,147 | — |
Agentic & Tool Use Claude Opus 5.5 leads
Claude Opus 5.5: 45.3 (#15), Qwen3 235B-A22B: 33.9 (#51)
| Benchmark | Claude Opus 5.5 | Qwen3 235B-A22B |
|---|---|---|
| Vending-Bench 2 | 9,235 | -11.34 |
| APEX-Agents | 73.5% | — |
| Berkeley Function Calling Leaderboard | — | 52.1% |
| GDP.pdf | 30.6% | — |
Reasoning Claude Opus 5.5 leads
Claude Opus 5.5: 80.2 (#3), Qwen3 235B-A22B: 15.7 (#311)
| Benchmark | Claude Opus 5.5 | Qwen3 235B-A22B |
|---|---|---|
| ARC-AGI-2 | 93.3% | 1.3% |
| ARC-AGI-1 | 98.5% | 11% |
| CritPt | 31.7% | 0% |
| LMArena Hard Prompts | 1535 | 1433 |
| Mystery Game Puzzles | 71% | 9% |
| DTBench | 98.9% | 80.3% |
| LMCA | 68.2% | 29.3% |
| Epoch Capabilities Index | 167.33 | 143.85 |
| SimpleBench | — | 31% |
| Kagi LLM Benchmark | — | 69.4% |
| NYT Connections (extended) | 88.5% | — |
| Chess Puzzles | — | 12% |
| EBR-Bench | 71.4% | — |
| ForecastBench | — | 59.7 |
Math Claude Opus 5.5 leads
Claude Opus 5.5: 91.8 (#3), Qwen3 235B-A22B: 50.4 (#57)
| Benchmark | Claude Opus 5.5 | Qwen3 235B-A22B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 86.7% |
| LMArena Math | 1506 | 1432 |
| FrontierMath (Tiers 1-3) | 91.2% | — |
| FrontierMath Tier 4 | 95% | — |
| ProofBench | 100% | — |
| Omni-MATH | — | 71.8% |
| MATH Level 5 | — | 68.9% |
| FrontierMath (Feb 2025 set) | — | 8.5% |
| FrontierMath Erdős | 2.9% | — |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Claude Opus 5.5 leads
Claude Opus 5.5: 66.4 (#10), Qwen3 235B-A22B: 49.6 (#73)
| Benchmark | Claude Opus 5.5 | Qwen3 235B-A22B |
|---|---|---|
| GPQA Diamond | 90.6% | 80.1% |
| SimpleQA Verified | 72.2% | 40.4% |
| LMArena Expert | 1547 | 1463 |
| MMLU-Pro | — | 84.4% |
| Confabulations | — | 15.6% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 72.7% |
Multimodal Not comparable
Claude Opus 5.5: 57.8 (#1), Qwen3 235B-A22B: —
| Benchmark | Claude Opus 5.5 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Vision | 1321 | — |
| Blueprint-Bench 2 | 51.2% | — |
| Furniture Assembly | 83.3% | — |
Multilingual Claude Opus 5.5 leads
Claude Opus 5.5: 59.1 (#2), Qwen3 235B-A22B: 52.3 (#89)
| Benchmark | Claude Opus 5.5 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1507 | 1409 |
| LMArena Chinese | 1588 | 1481 |
| LMArena French | 1514 | 1445 |
| LMArena Russian | 1520 | 1411 |
| LMArena Spanish | 1507 | 1430 |
| LMArena German | — | 1433 |
| LMArena Japanese | — | 1399 |
| LMArena Korean | — | 1391 |
Instruction Following Claude Opus 5.5 leads
Claude Opus 5.5: 80.0 (#3), Qwen3 235B-A22B: 72.6 (#136)
| Benchmark | Claude Opus 5.5 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Instruction Following | 1537 | 1408 |
| IFEval | — | 83.5% |
Long Context Too close to call
Claude Opus 5.5: 47.1 (#19), Qwen3 235B-A22B: 46.1 (#26)
| Benchmark | Claude Opus 5.5 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1532 | 1426 |
| Fiction.LiveBench | — | 75% |
Writing & Preference Claude Opus 5.5 leads
Claude Opus 5.5: 78.2 (#3), Qwen3 235B-A22B: 59.6 (#108)
| Benchmark | Claude Opus 5.5 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1515 | 1419 |
| LMArena Creative Writing | 1533 | 1384 |
| EQ-Bench Creative Writing | 2050 | 1366 |
| LMArena Multi-Turn | 1499 | 1432 |
| Short-Story Creative Writing | — | 83% |
| WildBench | — | 86.6% |
Frequently asked questions
Is Claude Opus 5.5 better than Qwen3 235B-A22B?
Claude Opus 5.5 is the stronger model overall, scoring 68.6 to 43.5 on the Noometry Index. Qwen3 235B-A22B costs 6.5× less per token, which makes it the better buy when Claude Opus 5.5's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 5.5 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 Opus 5.5 lists at $4 and $20.
Is Claude Opus 5.5 or Qwen3 235B-A22B better for coding?
Claude Opus 5.5 scores higher on coding benchmarks: 71.9 versus 44.3 in the Noometry coding category.
Which has the bigger context window?
Claude Opus 5.5 does, with 1M tokens against 131K.
How many benchmarks do Claude Opus 5.5 and Qwen3 235B-A22B share?
27 benchmarks have published results for both models. Claude Opus 5.5 has 44 scored results on Noometry and Qwen3 235B-A22B has 49.