Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
Claude Opus 4.6 is clearly ahead on the aggregate, 90 to 51. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Claude Opus 4.6's sharpest advantage is in coding, where it averages 82 against 41. The single biggest benchmark swing on the page is SWE-bench Verified, 80 to 41.
Claude Opus 4.6 is also the more expensive model on tokens at $15.00 input / $75.00 output per 1M tokens, versus $15.00 input / $60.00 output per 1M tokens for o1. o1 is the reasoning model in the pair, while Claude Opus 4.6 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. Claude Opus 4.6 gives you the larger context window at 1M, compared with 200K for o1.
Pick Claude Opus 4.6 if you want the stronger benchmark profile. o1 only becomes the better choice if you want the cheaper token bill or you want the stronger reasoning-first profile.
Claude Opus 4.6
85.7
o1
83.8
Claude Opus 4.6
82
o1
41
Claude Opus 4.6
97.3
o1
74.3
Claude Opus 4.6
95
o1
92.2
Claude Opus 4.6 is ahead overall, 90 to 51. The biggest single separator in this matchup is SWE-bench Verified, where the scores are 80 and 41.
Claude Opus 4.6 has the edge for knowledge tasks in this comparison, averaging 85.7 versus 83.8. Inside this category, GPQA is the benchmark that creates the most daylight between them.
Claude Opus 4.6 has the edge for coding in this comparison, averaging 82 versus 41. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.
Claude Opus 4.6 has the edge for math in this comparison, averaging 97.3 versus 74.3. Inside this category, AIME 2024 is the benchmark that creates the most daylight between them.
Claude Opus 4.6 has the edge for instruction following in this comparison, averaging 95 versus 92.2. Inside this category, IFEval 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.