Head-to-head comparison across 3benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
Claude Opus 4.7
86
GPT-5.5 Pro
100
Verified leaderboard positions: Claude Opus 4.7 #6 · GPT-5.5 Pro unranked
Pick GPT-5.5 Pro if you want the stronger benchmark profile. Claude Opus 4.7 only becomes the better choice if knowledge is the priority or you want the cheaper token bill.
Agentic
+15.2 difference
Knowledge
+11.0 difference
Math
+8.6 difference
Claude Opus 4.7
GPT-5.5 Pro
$5 / $25
$30 / $180
N/A
N/A
N/A
N/A
1M
1M
Pick GPT-5.5 Pro if you want the stronger benchmark profile. Claude Opus 4.7 only becomes the better choice if knowledge is the priority or you want the cheaper token bill.
GPT-5.5 Pro is clearly ahead on the provisional aggregate, 100 to 86. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
GPT-5.5 Pro's sharpest advantage is in agentic, where it averages 90.1 against 74.9. The single biggest benchmark swing on the page is BrowseComp, 79.3% to 90.1%. Claude Opus 4.7 does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.
GPT-5.5 Pro is also the more expensive model on tokens at $30.00 input / $180.00 output per 1M tokens, versus $5.00 input / $25.00 output per 1M tokens for Claude Opus 4.7. That is roughly 7.2x on output cost alone. GPT-5.5 Pro is the reasoning model in the pair, while Claude Opus 4.7 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-5.5 Pro is ahead on BenchLM's provisional leaderboard, 100 to 86. The biggest single separator in this matchup is BrowseComp, where the scores are 79.3% and 90.1%.
Claude Opus 4.7 has the edge for knowledge tasks in this comparison, averaging 68.2 versus 57.2. Inside this category, HLE w/o tools is the benchmark that creates the most daylight between them.
GPT-5.5 Pro has the edge for math in this comparison, averaging 52.4 versus 43.8. Inside this category, FrontierMath is the benchmark that creates the most daylight between them.
GPT-5.5 Pro has the edge for agentic tasks in this comparison, averaging 90.1 versus 74.9. Inside this category, BrowseComp 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.