Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
GLM-5
75
Winner · 2/8 categoriesQwen3.6 Plus
69
5/8 categoriesGLM-5· Qwen3.6 Plus
Pick GLM-5 if you want the stronger benchmark profile. Qwen3.6 Plus only becomes the better choice if multimodal & grounded is the priority or you need the larger 1M context window.
GLM-5 is clearly ahead on the aggregate, 75 to 69. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
GLM-5's sharpest advantage is in reasoning, where it averages 70.5 against 62. The single biggest benchmark swing on the page is QwenWebBench, 1315 to 1502. Qwen3.6 Plus does hit back in multimodal & grounded, so the answer changes if that is the part of the workload you care about most.
Qwen3.6 Plus is the reasoning model in the pair, while GLM-5 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 200K for GLM-5.
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 | GLM-5 | Qwen3.6 Plus |
|---|---|---|
| AgenticQwen3.6 Plus wins | ||
| Terminal-Bench 2.0 | 56.2% | 61.6% |
| BrowseComp | 62% | — |
| OSWorld-Verified | 58% | 62.5% |
| Claw-Eval | 57.7% | 58.7% |
| QwenClawBench | 54.1% | 57.2% |
| QwenWebBench | 1315 | 1502 |
| TAU3-Bench | 65.6% | 70.7% |
| VITA-Bench | 37.0% | 44.3% |
| DeepPlanning | 14.6% | 41.5% |
| Toolathlon | 38% | 39.8% |
| MCP Atlas | 31.1% | 48.2% |
| MCP-Tasks | 60.8% | 74.1% |
| WideResearch | 69.8% | 74.3% |
| Tau2-Airline | 80.5% | — |
| Tau2-Telecom | 98.2% | — |
| PinchBench | 86.4% | — |
| BFCL v4 | 70.8% | — |
| CodingQwen3.6 Plus wins | ||
| HumanEval | 80% | — |
| SWE-bench Verified | 77.8% | 78.8% |
| SWE-bench Verified* | 72.8% | — |
| LiveCodeBench | 52% | — |
| LiveCodeBench v6 | 85.6% | 87.1% |
| SWE-bench Pro | 55.1% | 56.6% |
| SWE Multilingual | 73.3% | 73.8% |
| NL2Repo | 35.9% | 37.9% |
| SWE-Rebench | 62.8% | — |
| React Native Evals | 74.2% | — |
| Multimodal & GroundedQwen3.6 Plus wins | ||
| MMMU-Pro | 66% | 78.8% |
| OfficeQA Pro | 73% | — |
| 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% |
| ReasoningGLM-5 wins | ||
| MuSR | 82% | — |
| BBH | 83% | — |
| LongBench v2 | 60.8% | 62% |
| MRCRv2 | 73% | — |
| AI-Needle | 63.3% | 68.3% |
| KnowledgeGLM-5 wins | ||
| MMLU | 91.7% | — |
| GPQA | 86% | 90.4% |
| GPQA-D | 81.6% | — |
| SuperGPQA | 66.8% | 71.6% |
| MMLU-Pro | 85.7% | 88.5% |
| MMLU-Pro (Arcee) | 85.8% | — |
| MMLU-Redux | 94.4% | 94.5% |
| C-Eval | 92.8% | 93.3% |
| HLE | 27.2% | 28.8% |
| FrontierScience | 74% | — |
| SimpleQA | 84% | — |
| Instruction FollowingQwen3.6 Plus wins | ||
| IFEval | 92.6% | 94.3% |
| IFBench | 72.3% | 74.2% |
| MultilingualQwen3.6 Plus wins | ||
| MGSM | 84% | — |
| MMLU-ProX | 83.1% | 84.7% |
| NOVA-63 | 55.1% | 57.9% |
| INCLUDE | 84.9% | 85.1% |
| PolyMath | 65.2% | 77.4% |
| VWT2k-lite | 82.1% | 84.3% |
| MAXIFE | 85.6% | 88.2% |
| Mathematics | ||
| AIME 2023 | 88% | — |
| AIME 2024 | 90% | — |
| AIME 2025 | 93.3% | — |
| AIME26 | 95.8% | 95.3% |
| AIME25 (Arcee) | 93.3% | — |
| HMMT Feb 2023 | 84% | — |
| HMMT Feb 2024 | 86% | — |
| HMMT Feb 2025 | 85% | — |
| HMMT Feb 2025 | 97.5% | 96.7% |
| HMMT Nov 2025 | 96.9% | 94.6% |
| HMMT Feb 2026 | 86.4% | 87.8% |
| MMAnswerBench | 82.5% | 83.8% |
| BRUMO 2025 | 87% | — |
| MATH-500 | 97.4% | — |
GLM-5 is ahead overall, 75 to 69. The biggest single separator in this matchup is QwenWebBench, where the scores are 1315 and 1502.
GLM-5 has the edge for knowledge tasks in this comparison, averaging 67.7 versus 66. Inside this category, SuperGPQA 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 60.4. Inside this category, NL2Repo is the benchmark that creates the most daylight between them.
GLM-5 has the edge for reasoning in this comparison, averaging 70.5 versus 62. Inside this category, AI-Needle 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 58.3. Inside this category, QwenWebBench 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 69.2. 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 92.6. Inside this category, IFBench 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 83.4. Inside this category, PolyMath 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.