Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Step 3.5 Flash finishes one point ahead overall, 66 to 65. That is enough to call, but not enough to treat as a blowout. This matchup comes down to a few meaningful edges rather than one model dominating the board.
Step 3.5 Flash's sharpest advantage is in mathematics, where it averages 84.5 against 26.4. The single biggest benchmark swing on the page is AIME 2024, 87 to 26.4. GPT-4.1 does hit back in multimodal & grounded, so the answer changes if that is the part of the workload you care about most.
GPT-4.1 is also the more expensive model on tokens at $2.00 input / $8.00 output per 1M tokens, versus $0.10 input / $0.30 output per 1M tokens for Step 3.5 Flash. That is roughly 26.7x on output cost alone. GPT-4.1 gives you the larger context window at 1M, compared with 256K for Step 3.5 Flash.
Pick Step 3.5 Flash if you want the stronger benchmark profile. GPT-4.1 only becomes the better choice if multimodal & grounded is the priority or you need the larger 1M context window.
Step 3.5 Flash
60.2
GPT-4.1
64.7
Step 3.5 Flash
47.1
GPT-4.1
51.7
Step 3.5 Flash
66.7
GPT-4.1
73.6
Step 3.5 Flash
78.3
GPT-4.1
80.9
Step 3.5 Flash
60.8
GPT-4.1
63.3
Step 3.5 Flash
87
GPT-4.1
87.4
Step 3.5 Flash
82.8
GPT-4.1
69
Step 3.5 Flash
84.5
GPT-4.1
26.4
Step 3.5 Flash is ahead overall, 66 to 65. The biggest single separator in this matchup is AIME 2024, where the scores are 87 and 26.4.
GPT-4.1 has the edge for knowledge tasks in this comparison, averaging 63.3 versus 60.8. Inside this category, GPQA is the benchmark that creates the most daylight between them.
GPT-4.1 has the edge for coding in this comparison, averaging 51.7 versus 47.1. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.
Step 3.5 Flash has the edge for math in this comparison, averaging 84.5 versus 26.4. Inside this category, AIME 2024 is the benchmark that creates the most daylight between them.
GPT-4.1 has the edge for reasoning in this comparison, averaging 80.9 versus 78.3. Inside this category, MRCRv2 is the benchmark that creates the most daylight between them.
GPT-4.1 has the edge for agentic tasks in this comparison, averaging 64.7 versus 60.2. Inside this category, OSWorld-Verified is the benchmark that creates the most daylight between them.
GPT-4.1 has the edge for multimodal and grounded tasks in this comparison, averaging 73.6 versus 66.7. Inside this category, OfficeQA Pro is the benchmark that creates the most daylight between them.
GPT-4.1 has the edge for instruction following in this comparison, averaging 87.4 versus 87. Inside this category, IFEval is the benchmark that creates the most daylight between them.
Step 3.5 Flash has the edge for multilingual tasks in this comparison, averaging 82.8 versus 69. 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.