Head-to-head comparison across 4benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
Claude Mythos Preview
99
Kimi K2.5 (Reasoning)
79
Verified leaderboard positions: Claude Mythos Preview #1 · Kimi K2.5 (Reasoning) unranked
Pick Claude Mythos Preview if you want the stronger benchmark profile. Kimi K2.5 (Reasoning) only becomes the better choice if knowledge is the priority.
Agentic
+27.8 difference
Coding
+7.0 difference
Knowledge
+12.4 difference
Multimodal
+14.2 difference
Claude Mythos Preview
Kimi K2.5 (Reasoning)
$25 / $125
$null / $null
N/A
N/A
N/A
N/A
1M
128K
Pick Claude Mythos Preview if you want the stronger benchmark profile. Kimi K2.5 (Reasoning) only becomes the better choice if knowledge is the priority.
Claude Mythos Preview is clearly ahead on the provisional aggregate, 99 to 79. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Claude Mythos Preview's sharpest advantage is in agentic, where it averages 82.4 against 54.6. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 82% to 50.8%. Kimi K2.5 (Reasoning) does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.
Claude Mythos Preview gives you the larger context window at 1M, compared with 128K for Kimi K2.5 (Reasoning).
Claude Mythos Preview is ahead on BenchLM's provisional leaderboard, 99 to 79. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 82% and 50.8%.
Kimi K2.5 (Reasoning) has the edge for knowledge tasks in this comparison, averaging 87.3 versus 74.9. Inside this category, GPQA is the benchmark that creates the most daylight between them.
Claude Mythos Preview has the edge for coding in this comparison, averaging 83.8 versus 76.8. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.
Claude Mythos Preview has the edge for agentic tasks in this comparison, averaging 82.4 versus 54.6. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Claude Mythos Preview has the edge for multimodal and grounded tasks in this comparison, averaging 92.7 versus 78.5. Inside this category, MMMU-Pro 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.