Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Step 3.5 Flash is clearly ahead on the aggregate, 66 to 33. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Step 3.5 Flash's sharpest advantage is in mathematics, where it averages 84.5 against 42.3. The single biggest benchmark swing on the page is HumanEval, 77 to 17.
Step 3.5 Flash is also the more expensive model on tokens at $0.10 input / $0.30 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for LFM2.5-1.2B-Thinking. That is roughly Infinityx on output cost alone. LFM2.5-1.2B-Thinking 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 32K for LFM2.5-1.2B-Thinking.
Pick Step 3.5 Flash if you want the stronger benchmark profile. LFM2.5-1.2B-Thinking only becomes the better choice if you want the cheaper token bill or you want the stronger reasoning-first profile.
Step 3.5 Flash
60.2
LFM2.5-1.2B-Thinking
34.1
Step 3.5 Flash
47.1
LFM2.5-1.2B-Thinking
8.2
Step 3.5 Flash
66.7
LFM2.5-1.2B-Thinking
32.4
Step 3.5 Flash
78.3
LFM2.5-1.2B-Thinking
38.4
Step 3.5 Flash
60.8
LFM2.5-1.2B-Thinking
27
Step 3.5 Flash
87
LFM2.5-1.2B-Thinking
72
Step 3.5 Flash
82.8
LFM2.5-1.2B-Thinking
60.7
Step 3.5 Flash
84.5
LFM2.5-1.2B-Thinking
42.3
Step 3.5 Flash is ahead overall, 66 to 33. The biggest single separator in this matchup is HumanEval, where the scores are 77 and 17.
Step 3.5 Flash has the edge for knowledge tasks in this comparison, averaging 60.8 versus 27. Inside this category, MMLU is the benchmark that creates the most daylight between them.
Step 3.5 Flash has the edge for coding in this comparison, averaging 47.1 versus 8.2. Inside this category, HumanEval 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 42.3. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.
Step 3.5 Flash has the edge for reasoning in this comparison, averaging 78.3 versus 38.4. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.
Step 3.5 Flash has the edge for agentic tasks in this comparison, averaging 60.2 versus 34.1. Inside this category, BrowseComp is the benchmark that creates the most daylight between them.
Step 3.5 Flash has the edge for multimodal and grounded tasks in this comparison, averaging 66.7 versus 32.4. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
Step 3.5 Flash has the edge for instruction following in this comparison, averaging 87 versus 72. 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 60.7. Inside this category, MGSM 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.