Head-to-head comparison across 2benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
MAI-Thinking-1
65
Step 3.7 Flash
71
Verified leaderboard positions: MAI-Thinking-1 #23 · Step 3.7 Flash unranked
Pick Step 3.7 Flash if you want the stronger benchmark profile. MAI-Thinking-1 only becomes the better choice if coding is the priority.
Agentic
+19.9 difference
Coding
+14.7 difference
MAI-Thinking-1
Step 3.7 Flash
N/A
$0.2 / $1.15
N/A
N/A
N/A
N/A
256K
256K
Pick Step 3.7 Flash if you want the stronger benchmark profile. MAI-Thinking-1 only becomes the better choice if coding is the priority.
Step 3.7 Flash is clearly ahead on the provisional aggregate, 71 to 65. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Step 3.7 Flash's sharpest advantage is in agentic, where it averages 65.9 against 46. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 46% to 59.5%. MAI-Thinking-1 does hit back in coding, so the answer changes if that is the part of the workload you care about most.
Step 3.7 Flash is ahead on BenchLM's provisional leaderboard, 71 to 65. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 46% and 59.5%.
MAI-Thinking-1 has the edge for coding in this comparison, averaging 71 versus 56.3. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Step 3.7 Flash has the edge for agentic tasks in this comparison, averaging 65.9 versus 46. Inside this category, Terminal-Bench 2.0 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.