Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
o1-preview is clearly ahead on the aggregate, 77 to 66. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
o1-preview's sharpest advantage is in coding, where it averages 64.6 against 47.1. The single biggest benchmark swing on the page is SWE-bench Pro, 69 to 49.
o1-preview is the reasoning model in the pair, while Step 3.5 Flash 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. Step 3.5 Flash gives you the larger context window at 256K, compared with 200K for o1-preview.
Pick o1-preview if you want the stronger benchmark profile. Step 3.5 Flash only becomes the better choice if you need the larger 256K context window or you would rather avoid the extra latency and token burn of a reasoning model.
o1-preview
75.4
Step 3.5 Flash
60.2
o1-preview
64.6
Step 3.5 Flash
47.1
o1-preview
75.6
Step 3.5 Flash
66.7
o1-preview
86.8
Step 3.5 Flash
78.3
o1-preview
71.3
Step 3.5 Flash
60.8
o1-preview
88
Step 3.5 Flash
87
o1-preview
87.4
Step 3.5 Flash
82.8
o1-preview
93.5
Step 3.5 Flash
84.5
o1-preview is ahead overall, 77 to 66. The biggest single separator in this matchup is SWE-bench Pro, where the scores are 69 and 49.
o1-preview has the edge for knowledge tasks in this comparison, averaging 71.3 versus 60.8. Inside this category, HLE is the benchmark that creates the most daylight between them.
o1-preview has the edge for coding in this comparison, averaging 64.6 versus 47.1. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.
o1-preview has the edge for math in this comparison, averaging 93.5 versus 84.5. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.
o1-preview has the edge for reasoning in this comparison, averaging 86.8 versus 78.3. Inside this category, LongBench v2 is the benchmark that creates the most daylight between them.
o1-preview has the edge for agentic tasks in this comparison, averaging 75.4 versus 60.2. Inside this category, OSWorld-Verified is the benchmark that creates the most daylight between them.
o1-preview has the edge for multimodal and grounded tasks in this comparison, averaging 75.6 versus 66.7. Inside this category, OfficeQA Pro is the benchmark that creates the most daylight between them.
o1-preview has the edge for instruction following in this comparison, averaging 88 versus 87. Inside this category, IFEval is the benchmark that creates the most daylight between them.
o1-preview has the edge for multilingual tasks in this comparison, averaging 87.4 versus 82.8. 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.