Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
GPT-5.4
82
Winner · 7/8 categoriesQwen3.6 Plus
69
0/8 categoriesGPT-5.4· Qwen3.6 Plus
Pick GPT-5.4 if you want the stronger benchmark profile. Qwen3.6 Plus only becomes the better choice if you want the cheaper token bill.
GPT-5.4 is clearly ahead on the aggregate, 82 to 69. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
GPT-5.4's sharpest advantage is in reasoning, where it averages 87.7 against 62. The single biggest benchmark swing on the page is SuperGPQA, 96% to 71.6%.
GPT-5.4 is also the more expensive model on tokens at $2.50 input / $15.00 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. GPT-5.4 gives you the larger context window at 1.05M, compared with 1M for Qwen3.6 Plus.
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 | GPT-5.4 | Qwen3.6 Plus |
|---|---|---|
| AgenticGPT-5.4 wins | ||
| Terminal-Bench 2.0 | 75.1% | 61.6% |
| BrowseComp | 82.7% | — |
| OSWorld-Verified | 75% | 62.5% |
| MCP Atlas | 67.2% | 48.2% |
| Toolathlon | 54.6% | 39.8% |
| Tau2-Telecom | 98.9% | — |
| Claw-Eval | 66.3% | 58.7% |
| QwenClawBench | — | 57.2% |
| QwenWebBench | — | 1502 |
| TAU3-Bench | — | 70.7% |
| VITA-Bench | — | 44.3% |
| DeepPlanning | — | 41.5% |
| MCP-Tasks | — | 74.1% |
| WideResearch | — | 74.3% |
| CodingGPT-5.4 wins | ||
| HumanEval | 95% | — |
| SWE-bench Verified | 84% | 78.8% |
| LiveCodeBench | 84% | — |
| SWE-bench Pro | 57.7% | 56.6% |
| React Native Evals | 82.6% | — |
| SWE Multilingual | — | 73.8% |
| LiveCodeBench v6 | — | 87.1% |
| NL2Repo | — | 37.9% |
| Multimodal & GroundedGPT-5.4 wins | ||
| MMMU-Pro | 81.2% | 78.8% |
| OfficeQA Pro | 96% | — |
| MMMU-Pro w/ Python | 81.5% | — |
| 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% |
| SimpleVQA | — | 67.3% |
| 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% |
| ReasoningGPT-5.4 wins | ||
| MuSR | 94% | — |
| BBH | 97% | — |
| MRCRv2 | 97% | — |
| MRCR v2 64K-128K | 86% | — |
| MRCR v2 128K-256K | 79.3% | — |
| Graphwalks BFS 128K | 93.1% | — |
| Graphwalks Parents 128K | 89.8% | — |
| ARC-AGI-2 | 73.3% | — |
| AI-Needle | — | 68.3% |
| LongBench v2 | — | 62% |
| KnowledgeGPT-5.4 wins | ||
| MMLU | 99% | — |
| GPQA | 92.8% | 90.4% |
| SuperGPQA | 96% | 71.6% |
| MMLU-Pro | 93% | 88.5% |
| HLE | 48% | 28.8% |
| FrontierScience | 91% | — |
| HLE w/o tools | 39.8% | — |
| SimpleQA | 97% | — |
| MMLU-Redux | — | 94.5% |
| C-Eval | — | 93.3% |
| Instruction FollowingGPT-5.4 wins | ||
| IFEval | 96% | 94.3% |
| IFBench | — | 74.2% |
| MultilingualGPT-5.4 wins | ||
| MGSM | 96% | — |
| MMLU-ProX | 94% | 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 | 99% | — |
| HMMT Feb 2023 | 96% | — |
| HMMT Feb 2024 | 98% | — |
| HMMT Feb 2025 | 97% | — |
| BRUMO 2025 | 97% | — |
| MATH-500 | 99% | — |
| AIME26 | — | 95.3% |
| HMMT Feb 2025 | — | 96.7% |
| HMMT Nov 2025 | — | 94.6% |
| HMMT Feb 2026 | — | 87.8% |
| MMAnswerBench | — | 83.8% |
GPT-5.4 is ahead overall, 82 to 69. The biggest single separator in this matchup is SuperGPQA, where the scores are 96% and 71.6%.
GPT-5.4 has the edge for knowledge tasks in this comparison, averaging 83.1 versus 66. Inside this category, SuperGPQA is the benchmark that creates the most daylight between them.
GPT-5.4 has the edge for coding in this comparison, averaging 73.9 versus 64.9. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.
GPT-5.4 has the edge for reasoning in this comparison, averaging 87.7 versus 62. Qwen3.6 Plus stays close enough that the answer can still flip depending on your workload.
GPT-5.4 has the edge for agentic tasks in this comparison, averaging 77 versus 62. Inside this category, MCP Atlas is the benchmark that creates the most daylight between them.
GPT-5.4 has the edge for multimodal and grounded tasks in this comparison, averaging 87.9 versus 78.8. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
GPT-5.4 has the edge for instruction following in this comparison, averaging 96 versus 94.3. Inside this category, IFEval is the benchmark that creates the most daylight between them.
GPT-5.4 has the edge for multilingual tasks in this comparison, averaging 94.7 versus 84.7. Inside this category, MMLU-ProX is the benchmark that creates the most daylight between them.
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.