Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
GPT-5.2 Pro is clearly ahead on the aggregate, 90 to 75. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
GPT-5.2 Pro's sharpest advantage is in multimodal & grounded, where it averages 96 against 70.8. The single biggest benchmark swing on the page is MMMU-Pro, 96 to 64.
GPT-5.2 Pro gives you the larger context window at 400K, compared with 128K for Qwen3.5 397B (Reasoning).
Pick GPT-5.2 Pro if you want the stronger benchmark profile. Qwen3.5 397B (Reasoning) only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.
GPT-5.2 Pro
85.9
Qwen3.5 397B (Reasoning)
74.8
GPT-5.2 Pro
84.8
Qwen3.5 397B (Reasoning)
62.3
GPT-5.2 Pro
96
Qwen3.5 397B (Reasoning)
70.8
GPT-5.2 Pro
95.2
Qwen3.5 397B (Reasoning)
84.2
GPT-5.2 Pro
81.5
Qwen3.5 397B (Reasoning)
70.1
GPT-5.2 Pro
95
Qwen3.5 397B (Reasoning)
89
GPT-5.2 Pro
93.4
Qwen3.5 397B (Reasoning)
87.8
GPT-5.2 Pro
98.2
Qwen3.5 397B (Reasoning)
92.5
GPT-5.2 Pro is ahead overall, 90 to 75. The biggest single separator in this matchup is MMMU-Pro, where the scores are 96 and 64.
GPT-5.2 Pro has the edge for knowledge tasks in this comparison, averaging 81.5 versus 70.1. Inside this category, HLE is the benchmark that creates the most daylight between them.
GPT-5.2 Pro has the edge for coding in this comparison, averaging 84.8 versus 62.3. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.
GPT-5.2 Pro has the edge for math in this comparison, averaging 98.2 versus 92.5. Inside this category, HMMT Feb 2023 is the benchmark that creates the most daylight between them.
GPT-5.2 Pro has the edge for reasoning in this comparison, averaging 95.2 versus 84.2. Inside this category, LongBench v2 is the benchmark that creates the most daylight between them.
GPT-5.2 Pro has the edge for agentic tasks in this comparison, averaging 85.9 versus 74.8. Inside this category, OSWorld-Verified is the benchmark that creates the most daylight between them.
GPT-5.2 Pro has the edge for multimodal and grounded tasks in this comparison, averaging 96 versus 70.8. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
GPT-5.2 Pro has the edge for instruction following in this comparison, averaging 95 versus 89. Inside this category, IFEval is the benchmark that creates the most daylight between them.
GPT-5.2 Pro has the edge for multilingual tasks in this comparison, averaging 93.4 versus 87.8. 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.