Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
GPT-5.4 mini
68
1/8 categoriesQwen3.6 Plus
69
Winner · 5/8 categoriesGPT-5.4 mini· Qwen3.6 Plus
Pick Qwen3.6 Plus if you want the stronger benchmark profile. GPT-5.4 mini only becomes the better choice if agentic is the priority.
Qwen3.6 Plus finishes one point ahead overall, 69 to 68. That is enough to call, but not enough to treat as a blowout. This matchup comes down to a few meaningful edges rather than one model dominating the board.
Qwen3.6 Plus's sharpest advantage is in reasoning, where it averages 62 against 40.7. The single biggest benchmark swing on the page is HLE, 41.5% to 28.8%. GPT-5.4 mini does hit back in agentic, so the answer changes if that is the part of the workload you care about most.
GPT-5.4 mini is also the more expensive model on tokens at $0.75 input / $4.50 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 gives you the larger context window at 1M, compared with 400K for GPT-5.4 mini.
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 mini | Qwen3.6 Plus |
|---|---|---|
| AgenticGPT-5.4 mini wins | ||
| Terminal-Bench 2.0 | 60% | 61.6% |
| OSWorld-Verified | 72.1% | 62.5% |
| MCP Atlas | 57.7% | 48.2% |
| Toolathlon | 42.9% | 39.8% |
| Tau2-Telecom | 93.4% | — |
| Claw-Eval | — | 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% |
| CodingQwen3.6 Plus wins | ||
| SWE-bench Pro | 54.4% | 56.6% |
| SWE-bench Verified | — | 78.8% |
| SWE Multilingual | — | 73.8% |
| LiveCodeBench v6 | — | 87.1% |
| NL2Repo | — | 37.9% |
| Multimodal & GroundedQwen3.6 Plus wins | ||
| MMMU-Pro | 76.6% | 78.8% |
| MMMU-Pro w/ Python | 78% | — |
| 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% |
| ReasoningQwen3.6 Plus wins | ||
| MRCRv2 | 40.7% | — |
| MRCR v2 64K-128K | 47.7% | — |
| MRCR v2 128K-256K | 33.6% | — |
| Graphwalks BFS 128K | 76.3% | — |
| Graphwalks Parents 128K | 71.5% | — |
| AI-Needle | — | 68.3% |
| LongBench v2 | — | 62% |
| KnowledgeQwen3.6 Plus wins | ||
| GPQA | 88% | 90.4% |
| HLE | 41.5% | 28.8% |
| HLE w/o tools | 28.2% | — |
| SuperGPQA | — | 71.6% |
| MMLU-Pro | — | 88.5% |
| MMLU-Redux | — | 94.5% |
| C-Eval | — | 93.3% |
| Instruction FollowingQwen3.6 Plus wins | ||
| IFEval | 87.4% | 94.3% |
| IFBench | — | 74.2% |
| Multilingual | ||
| MMLU-ProX | — | 84.7% |
| NOVA-63 | — | 57.9% |
| INCLUDE | — | 85.1% |
| PolyMath | — | 77.4% |
| VWT2k-lite | — | 84.3% |
| MAXIFE | — | 88.2% |
| Mathematics | ||
| MATH-500 | 97.4% | — |
| AIME26 | — | 95.3% |
| HMMT Feb 2025 | — | 96.7% |
| HMMT Nov 2025 | — | 94.6% |
| HMMT Feb 2026 | — | 87.8% |
| MMAnswerBench | — | 83.8% |
Qwen3.6 Plus is ahead overall, 69 to 68. The biggest single separator in this matchup is HLE, where the scores are 41.5% and 28.8%.
Qwen3.6 Plus has the edge for knowledge tasks in this comparison, averaging 66 versus 57.4. Inside this category, HLE is the benchmark that creates the most daylight between them.
Qwen3.6 Plus has the edge for coding in this comparison, averaging 64.9 versus 54.4. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.
Qwen3.6 Plus has the edge for reasoning in this comparison, averaging 62 versus 40.7. GPT-5.4 mini stays close enough that the answer can still flip depending on your workload.
GPT-5.4 mini has the edge for agentic tasks in this comparison, averaging 65.6 versus 62. Inside this category, OSWorld-Verified is the benchmark that creates the most daylight between them.
Qwen3.6 Plus has the edge for multimodal and grounded tasks in this comparison, averaging 78.8 versus 76.6. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
Qwen3.6 Plus has the edge for instruction following in this comparison, averaging 94.3 versus 87.4. Inside this category, IFEval 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.