Head-to-head comparison across 5benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
GPT-5.2
79
Qwen3.5 397B
63
Verified leaderboard positions: GPT-5.2 unranked · Qwen3.5 397B #19
Pick GPT-5.2 if you want the stronger benchmark profile. Qwen3.5 397B only becomes the better choice if reasoning is the priority or you want the cheaper token bill.
Agentic
+1.0 difference
Coding
+4.4 difference
Reasoning
+10.3 difference
Knowledge
+27.2 difference
Multimodal
+0.7 difference
GPT-5.2
Qwen3.5 397B
$1.75 / $14
$0.6 / $3.6
73 t/s
96 t/s
130.34s
2.44s
400K
128K
Pick GPT-5.2 if you want the stronger benchmark profile. Qwen3.5 397B only becomes the better choice if reasoning is the priority or you want the cheaper token bill.
GPT-5.2 is clearly ahead on the provisional aggregate, 79 to 63. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
GPT-5.2's sharpest advantage is in knowledge, where it averages 92.4 against 65.2. The single biggest benchmark swing on the page is SWE-bench Pro, 55.6% to 50.9%. Qwen3.5 397B does hit back in reasoning, so the answer changes if that is the part of the workload you care about most.
GPT-5.2 is also the more expensive model on tokens at $1.75 input / $14.00 output per 1M tokens, versus $0.60 input / $3.60 output per 1M tokens for Qwen3.5 397B. That is roughly 3.9x on output cost alone. GPT-5.2 is the reasoning model in the pair, while Qwen3.5 397B 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. GPT-5.2 gives you the larger context window at 400K, compared with 128K for Qwen3.5 397B.
GPT-5.2 is ahead on BenchLM's provisional leaderboard, 79 to 63. The biggest single separator in this matchup is SWE-bench Pro, where the scores are 55.6% and 50.9%.
GPT-5.2 has the edge for knowledge tasks in this comparison, averaging 92.4 versus 65.2. Inside this category, AA-Omniscience Index is the benchmark that creates the most daylight between them.
GPT-5.2 has the edge for coding in this comparison, averaging 64.7 versus 60.3. Inside this category, Terminal-Bench Hard is the benchmark that creates the most daylight between them.
Qwen3.5 397B has the edge for reasoning in this comparison, averaging 63.2 versus 52.9. Inside this category, AA-LCR is the benchmark that creates the most daylight between them.
Qwen3.5 397B has the edge for agentic tasks in this comparison, averaging 56.2 versus 55.2. Inside this category, GDPval-AA is the benchmark that creates the most daylight between them.
GPT-5.2 has the edge for multimodal and grounded tasks in this comparison, averaging 80.3 versus 79.6. Inside this category, V* is the benchmark that creates the most daylight between them.
For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.