Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Claude Opus 4.6
84
Winner · 6/8 categoriesQwen3.6 Plus
69
0/8 categoriesClaude Opus 4.6· Qwen3.6 Plus
Pick Claude Opus 4.6 if you want the stronger benchmark profile. Qwen3.6 Plus only becomes the better choice if you want the cheaper token bill or you want the stronger reasoning-first profile.
Claude Opus 4.6 is clearly ahead on the aggregate, 84 to 69. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Claude Opus 4.6's sharpest advantage is in reasoning, where it averages 82.4 against 62. The single biggest benchmark swing on the page is LongBench v2, 92% to 62%.
Claude Opus 4.6 is also the more expensive model on tokens at $15.00 input / $75.00 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Qwen3.6 Plus. That is roughly Infinityx on output cost alone. Qwen3.6 Plus is the reasoning model in the pair, while Claude Opus 4.6 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use.
BenchLM keeps the benchmark table and the operator tradeoffs on the same page so a better score does not hide a materially slower, pricier, or smaller-context model.
Runtime metrics show N/A when BenchLM does not have a sourced snapshot for that exact model. The scoring rules and freshness policy are documented on the methodology page.
| Benchmark | Claude Opus 4.6 | Qwen3.6 Plus |
|---|---|---|
| AgenticClaude Opus 4.6 wins | ||
| Terminal-Bench 2.0 | 65.4% | 61.6% |
| BrowseComp | 84% | — |
| BrowseComp-VL | 35.9% | — |
| OSWorld | 72.2% | — |
| Tau2-Airline | 82.0% | — |
| Tau2-Telecom | 92.1% | — |
| PinchBench | 93.3% | — |
| BFCL v4 | 77.0% | — |
| AndroidWorld | 62.0% | — |
| WebVoyager | 88.0% | — |
| Claw-Eval | 66.3% | 58.7% |
| QwenClawBench | — | 57.2% |
| QwenWebBench | — | 1502 |
| TAU3-Bench | — | 70.7% |
| VITA-Bench | — | 44.3% |
| DeepPlanning | — | 41.5% |
| Toolathlon | — | 39.8% |
| MCP Atlas | — | 48.2% |
| MCP-Tasks | — | 74.1% |
| WideResearch | — | 74.3% |
| OSWorld-Verified | — | 62.5% |
| CodingClaude Opus 4.6 wins | ||
| SWE-bench Verified | 80.8% | 78.8% |
| SWE-bench Verified* | 75.6% | — |
| LiveCodeBench | 76% | — |
| FLTEval | 39.6% | — |
| SWE-Rebench | 65.3% | — |
| React Native Evals | 84.4% | — |
| SWE-bench Pro | — | 56.6% |
| SWE Multilingual | — | 73.8% |
| LiveCodeBench v6 | — | 87.1% |
| NL2Repo | — | 37.9% |
| Multimodal & GroundedClaude Opus 4.6 wins | ||
| MMMU-Pro | 77.3% | 78.8% |
| OfficeQA Pro | 94% | — |
| Design2Code | 77.3% | — |
| Flame-VLM-Code | 98.8% | — |
| Vision2Web | 43.5% | — |
| MMSearch | 63.8% | — |
| MMSearch-Plus | 25.6% | — |
| SimpleVQA | 63.2% | 67.3% |
| V* | 66.5% | — |
| MMMU | — | 86.0% |
| RealWorldQA | — | 85.4% |
| OmniDocBench 1.5 | — | 91.2% |
| Video-MME (with subtitle) | — | 87.8% |
| Video-MME (w/o subtitle) | — | 84.2% |
| MathVision | — | 88.0% |
| We-Math | — | 89.0% |
| DynaMath | — | 88.0% |
| MStar | — | 83.3% |
| ChatCVQA | — | 81.5% |
| MMLongBench-Doc | — | 62.0% |
| CC-OCR | — | 83.4% |
| AI2D_TEST | — | 94.4% |
| CountBench | — | 97.6% |
| RefCOCO (avg) | — | 93.5% |
| ODINW13 | — | 51.8% |
| ERQA | — | 65.7% |
| VideoMMMU | — | 84.0% |
| MLVU (M-Avg) | — | 86.7% |
| ScreenSpot Pro | — | 68.2% |
| ReasoningClaude Opus 4.6 wins | ||
| MuSR | 93% | — |
| BBH | 94% | — |
| LongBench v2 | 92% | 62% |
| MRCRv2 | 76% | — |
| ARC-AGI-2 | 68.8% | — |
| AI-Needle | — | 68.3% |
| KnowledgeClaude Opus 4.6 wins | ||
| MMLU | 99% | — |
| GPQA | 91.3% | 90.4% |
| GPQA-D | 89.2% | — |
| SuperGPQA | 95% | 71.6% |
| MMLU-Pro | 82% | 88.5% |
| MMLU-Pro (Arcee) | 89.1% | — |
| HLE | 53% | 28.8% |
| FrontierScience | 88% | — |
| SimpleQA | 72% | — |
| MMLU-Redux | — | 94.5% |
| C-Eval | — | 93.3% |
| Instruction Following | ||
| IFBench | 53.1% | 74.2% |
| IFEval | — | 94.3% |
| MultilingualClaude Opus 4.6 wins | ||
| MGSM | 96% | — |
| MMLU-ProX | — | 84.7% |
| NOVA-63 | — | 57.9% |
| INCLUDE | — | 85.1% |
| PolyMath | — | 77.4% |
| VWT2k-lite | — | 84.3% |
| MAXIFE | — | 88.2% |
| Mathematics | ||
| AIME 2023 | 99% | — |
| AIME 2024 | 99% | — |
| AIME 2025 | 98% | — |
| AIME25 (Arcee) | 99.8% | — |
| HMMT Feb 2023 | 95% | — |
| HMMT Feb 2024 | 97% | — |
| HMMT Feb 2025 | 96% | — |
| BRUMO 2025 | 96% | — |
| MATH-500 | 98% | — |
| AIME26 | — | 95.3% |
| HMMT Feb 2025 | — | 96.7% |
| HMMT Nov 2025 | — | 94.6% |
| HMMT Feb 2026 | — | 87.8% |
| MMAnswerBench | — | 83.8% |
Claude Opus 4.6 is ahead overall, 84 to 69. The biggest single separator in this matchup is LongBench v2, where the scores are 92% and 62%.
Claude Opus 4.6 has the edge for knowledge tasks in this comparison, averaging 77.8 versus 66. Inside this category, HLE is the benchmark that creates the most daylight between them.
Claude Opus 4.6 has the edge for coding in this comparison, averaging 72 versus 64.9. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.
Claude Opus 4.6 has the edge for reasoning in this comparison, averaging 82.4 versus 62. Inside this category, LongBench v2 is the benchmark that creates the most daylight between them.
Claude Opus 4.6 has the edge for agentic tasks in this comparison, averaging 72.6 versus 62. Inside this category, Claw-Eval is the benchmark that creates the most daylight between them.
Claude Opus 4.6 has the edge for multimodal and grounded tasks in this comparison, averaging 84.8 versus 78.8. Inside this category, SimpleVQA is the benchmark that creates the most daylight between them.
Claude Opus 4.6 has the edge for multilingual tasks in this comparison, averaging 96 versus 84.7. Qwen3.6 Plus stays close enough that the answer can still flip depending on your workload.
Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.
Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.