Head-to-head comparison across 1benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
Kimi K2.5 (Reasoning)
75
Mistral Medium 3.5 128B
78
Pick Mistral Medium 3.5 128B if you want the stronger benchmark profile. Kimi K2.5 (Reasoning) only becomes the better choice if you want the cheaper token bill.
Coding
+0.8 difference
Kimi K2.5 (Reasoning)
Mistral Medium 3.5 128B
$0.6 / $3
$1.5 / $7.5
N/A
N/A
N/A
N/A
128K
256K
Pick Mistral Medium 3.5 128B if you want the stronger benchmark profile. Kimi K2.5 (Reasoning) only becomes the better choice if you want the cheaper token bill.
Mistral Medium 3.5 128B has the cleaner provisional overall profile here, landing at 78 versus 75. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
Mistral Medium 3.5 128B's sharpest advantage is in coding, where it averages 77.6 against 76.8. The single biggest benchmark swing on the page is SWE-bench Verified, 76.8% to 77.6%.
Mistral Medium 3.5 128B is also the more expensive model on tokens at $1.50 input / $7.50 output per 1M tokens, versus $0.60 input / $3.00 output per 1M tokens for Kimi K2.5 (Reasoning). That is roughly 2.5x on output cost alone. Mistral Medium 3.5 128B gives you the larger context window at 256K, compared with 128K for Kimi K2.5 (Reasoning).
Mistral Medium 3.5 128B is ahead on BenchLM's provisional leaderboard, 78 to 75. The biggest single separator in this matchup is SWE-bench Verified, where the scores are 76.8% and 77.6%.
Mistral Medium 3.5 128B has the edge for coding in this comparison, averaging 77.6 versus 76.8. Inside this category, AA-SciCode 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.