Head-to-head comparison across 5benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
Claude Opus 4.7 (Adaptive)
90
GPT-5.2
81
Verified leaderboard positions: Claude Opus 4.7 (Adaptive) #5 · GPT-5.2 unranked
Pick Claude Opus 4.7 (Adaptive) if you want the stronger benchmark profile. GPT-5.2 only becomes the better choice if knowledge is the priority or you want the cheaper token bill.
Agentic
+19.7 difference
Coding
+8.2 difference
Reasoning
+22.9 difference
Knowledge
+24.2 difference
Multimodal
+16.0 difference
Claude Opus 4.7 (Adaptive)
GPT-5.2
$5 / $25
$1.75 / $14
N/A
73 t/s
N/A
130.34s
1M
400K
Pick Claude Opus 4.7 (Adaptive) if you want the stronger benchmark profile. GPT-5.2 only becomes the better choice if knowledge is the priority or you want the cheaper token bill.
Claude Opus 4.7 (Adaptive) is clearly ahead on the provisional aggregate, 90 to 81. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Claude Opus 4.7 (Adaptive)'s sharpest advantage is in reasoning, where it averages 75.8 against 52.9. The single biggest benchmark swing on the page is OSWorld-Verified, 78% to 47.3%. GPT-5.2 does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.
Claude Opus 4.7 (Adaptive) is also the more expensive model on tokens at $5.00 input / $25.00 output per 1M tokens, versus $1.75 input / $14.00 output per 1M tokens for GPT-5.2. Claude Opus 4.7 (Adaptive) gives you the larger context window at 1M, compared with 400K for GPT-5.2.
Claude Opus 4.7 (Adaptive) is ahead on BenchLM's provisional leaderboard, 90 to 81. The biggest single separator in this matchup is OSWorld-Verified, where the scores are 78% and 47.3%.
GPT-5.2 has the edge for knowledge tasks in this comparison, averaging 92.4 versus 68.2. Inside this category, GPQA is the benchmark that creates the most daylight between them.
Claude Opus 4.7 (Adaptive) has the edge for coding in this comparison, averaging 72.9 versus 64.7. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.
Claude Opus 4.7 (Adaptive) has the edge for reasoning in this comparison, averaging 75.8 versus 52.9. Inside this category, ARC-AGI-2 is the benchmark that creates the most daylight between them.
Claude Opus 4.7 (Adaptive) has the edge for agentic tasks in this comparison, averaging 74.9 versus 55.2. Inside this category, OSWorld-Verified 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 64.3. Inside this category, CharXiv 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.