Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
GPT-5.2-Codex
82
Winner · 6/8 categoriesQwen3.6 Plus
69
1/8 categoriesGPT-5.2-Codex· Qwen3.6 Plus
Pick GPT-5.2-Codex if you want the stronger benchmark profile. Qwen3.6 Plus only becomes the better choice if instruction following is the priority or you want the cheaper token bill.
GPT-5.2-Codex 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-5.2-Codex's sharpest advantage is in reasoning, where it averages 91.1 against 62. The single biggest benchmark swing on the page is SWE-bench Pro, 86% to 56.6%. Qwen3.6 Plus does hit back in instruction following, so the answer changes if that is the part of the workload you care about most.
GPT-5.2-Codex is also the more expensive model on tokens at $2.00 input / $8.00 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 gives you the larger context window at 1M, compared with 400K for GPT-5.2-Codex.
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-5.2-Codex | Qwen3.6 Plus |
|---|---|---|
| AgenticGPT-5.2-Codex wins | ||
| Terminal-Bench 2.0 | 90% | 61.6% |
| BrowseComp | 85% | — |
| OSWorld-Verified | 85% | 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-5.2-Codex wins | ||
| HumanEval | 95% | — |
| SWE-bench Verified | 76% | 78.8% |
| LiveCodeBench | 66% | — |
| SWE-bench Pro | 86% | 56.6% |
| SWE-Rebench | 56.8% | — |
| SWE Multilingual | — | 73.8% |
| LiveCodeBench v6 | — | 87.1% |
| NL2Repo | — | 37.9% |
| Multimodal & GroundedGPT-5.2-Codex wins | ||
| MMMU-Pro | 84% | 78.8% |
| OfficeQA Pro | 92% | — |
| 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-5.2-Codex wins | ||
| MuSR | 93% | — |
| BBH | 90% | — |
| LongBench v2 | 90% | 62% |
| MRCRv2 | 91% | — |
| AI-Needle | — | 68.3% |
| KnowledgeGPT-5.2-Codex wins | ||
| MMLU | 99% | — |
| GPQA | 97% | 90.4% |
| SuperGPQA | 95% | 71.6% |
| HLE | 26% | 28.8% |
| FrontierScience | 86% | — |
| SimpleQA | 95% | — |
| MMLU-Pro | — | 88.5% |
| MMLU-Redux | — | 94.5% |
| C-Eval | — | 93.3% |
| Instruction FollowingQwen3.6 Plus wins | ||
| IFEval | 92% | 94.3% |
| IFBench | — | 74.2% |
| MultilingualGPT-5.2-Codex wins | ||
| MGSM | 91% | — |
| MMLU-ProX | 87% | 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% | — |
| HMMT Feb 2023 | 95% | — |
| HMMT Feb 2024 | 97% | — |
| HMMT Feb 2025 | 96% | — |
| BRUMO 2025 | 96% | — |
| AIME26 | — | 95.3% |
| HMMT Feb 2025 | — | 96.7% |
| HMMT Nov 2025 | — | 94.6% |
| HMMT Feb 2026 | — | 87.8% |
| MMAnswerBench | — | 83.8% |
GPT-5.2-Codex is ahead overall, 82 to 69. The biggest single separator in this matchup is SWE-bench Pro, where the scores are 86% and 56.6%.
GPT-5.2-Codex has the edge for knowledge tasks in this comparison, averaging 72.9 versus 66. Inside this category, SuperGPQA is the benchmark that creates the most daylight between them.
GPT-5.2-Codex has the edge for coding in this comparison, averaging 69.3 versus 64.9. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.
GPT-5.2-Codex has the edge for reasoning in this comparison, averaging 91.1 versus 62. Inside this category, LongBench v2 is the benchmark that creates the most daylight between them.
GPT-5.2-Codex has the edge for agentic tasks in this comparison, averaging 87 versus 62. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
GPT-5.2-Codex has the edge for multimodal and grounded tasks in this comparison, averaging 87.6 versus 78.8. 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. Inside this category, IFEval is the benchmark that creates the most daylight between them.
GPT-5.2-Codex has the edge for multilingual tasks in this comparison, averaging 88.4 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.