Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
GPT-4o mini
54
1/8 categoriesQwen3.6 Plus
69
Winner · 4/8 categoriesGPT-4o mini· Qwen3.6 Plus
Pick Qwen3.6 Plus if you want the stronger benchmark profile. GPT-4o mini only becomes the better choice if coding is the priority or you would rather avoid the extra latency and token burn of a reasoning model.
Qwen3.6 Plus is clearly ahead on the aggregate, 69 to 54. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Qwen3.6 Plus's sharpest advantage is in multimodal & grounded, where it averages 78.8 against 60.2. The single biggest benchmark swing on the page is OSWorld-Verified, 44% to 62.5%. GPT-4o mini does hit back in coding, so the answer changes if that is the part of the workload you care about most.
GPT-4o mini is also the more expensive model on tokens at $0.15 input / $0.60 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 GPT-4o mini 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. Qwen3.6 Plus gives you the larger context window at 1M, compared with 128K for GPT-4o 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-4o mini | Qwen3.6 Plus |
|---|---|---|
| AgenticQwen3.6 Plus wins | ||
| Terminal-Bench 2.0 | 58% | 61.6% |
| BrowseComp | 49% | — |
| OSWorld-Verified | 44% | 62.5% |
| Claw-Eval | — | 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% |
| CodingGPT-4o mini wins | ||
| HumanEval | 87.2% | — |
| SWE-bench Pro | 65% | 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 | 66% | 78.8% |
| OfficeQA Pro | 53% | — |
| 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 | ||
| LongBench v2 | 49% | 62% |
| MRCRv2 | 50% | — |
| AI-Needle | — | 68.3% |
| Knowledge | ||
| MMLU | 82% | — |
| GPQA | — | 90.4% |
| SuperGPQA | — | 71.6% |
| MMLU-Pro | — | 88.5% |
| MMLU-Redux | — | 94.5% |
| C-Eval | — | 93.3% |
| HLE | — | 28.8% |
| Instruction Following | ||
| IFEval | — | 94.3% |
| IFBench | — | 74.2% |
| MultilingualQwen3.6 Plus wins | ||
| MGSM | 87% | — |
| MMLU-ProX | 68% | 84.7% |
| NOVA-63 | — | 57.9% |
| INCLUDE | — | 85.1% |
| PolyMath | — | 77.4% |
| VWT2k-lite | — | 84.3% |
| MAXIFE | — | 88.2% |
| Mathematics | ||
| 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 54. The biggest single separator in this matchup is OSWorld-Verified, where the scores are 44% and 62.5%.
GPT-4o mini has the edge for coding in this comparison, averaging 65 versus 64.9. 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 49.5. Inside this category, LongBench v2 is the benchmark that creates the most daylight between them.
Qwen3.6 Plus has the edge for agentic tasks in this comparison, averaging 62 versus 50.9. 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 60.2. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
Qwen3.6 Plus has the edge for multilingual tasks in this comparison, averaging 84.7 versus 74.7. 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.