Head-to-head comparison across 5benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
Kimi K2.5
64
MAI-Thinking-1
65
Verified leaderboard positions: Kimi K2.5 #16 · MAI-Thinking-1 #23
Pick MAI-Thinking-1 if you want the stronger benchmark profile. Kimi K2.5 only becomes the better choice if instruction following is the priority or you would rather avoid the extra latency and token burn of a reasoning model.
Agentic
+8.6 difference
Coding
+6.8 difference
Knowledge
+4.8 difference
Math
+0.9 difference
Inst. Following
+8.9 difference
Kimi K2.5
MAI-Thinking-1
$0.6 / $3
N/A
45 t/s
N/A
2.38s
N/A
256K
256K
Pick MAI-Thinking-1 if you want the stronger benchmark profile. Kimi K2.5 only becomes the better choice if instruction following is the priority or you would rather avoid the extra latency and token burn of a reasoning model.
MAI-Thinking-1 finishes one point ahead on BenchLM's provisional leaderboard, 65 to 64. 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.
MAI-Thinking-1's sharpest advantage is in coding, where it averages 71 against 64.2. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 50.8% to 46%. Kimi K2.5 does hit back in instruction following, so the answer changes if that is the part of the workload you care about most.
MAI-Thinking-1 is the reasoning model in the pair, while Kimi K2.5 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.
MAI-Thinking-1 is ahead on BenchLM's provisional leaderboard, 65 to 64. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 50.8% and 46%.
MAI-Thinking-1 has the edge for knowledge tasks in this comparison, averaging 69.9 versus 65.1. Inside this category, GPQA is the benchmark that creates the most daylight between them.
MAI-Thinking-1 has the edge for coding in this comparison, averaging 71 versus 64.2. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.
MAI-Thinking-1 has the edge for math in this comparison, averaging 97 versus 96.1. Inside this category, HMMT Feb 2026 is the benchmark that creates the most daylight between them.
Kimi K2.5 has the edge for agentic tasks in this comparison, averaging 54.6 versus 46. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Kimi K2.5 has the edge for instruction following in this comparison, averaging 93.9 versus 85. MAI-Thinking-1 stays close enough that the answer can still flip depending on your workload.
Estimates at 50,000 req/day · 1000 tokens/req average.
For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.