Kimi K2.5 (Reasoning)

kimi-k2-5 · 4 samples · combined / raw

Scoring

Choose the quality benchmark and final score formula for this model.

Cost adjustment

Tune formulas that account for benchmark cost.

Score over time

49.4 47.4 #1 · 48.4 · 2026-05-11 23:17:33#2 · 48.4 · 2026-05-12 00:00:09#3 · 48.4 · 2026-05-12 01:00:09#4 · 48.4 · 2026-05-12 02:00:11

Cost over time

$355 $353 #1 · $354 · 2026-05-11 23:17:33#2 · $354 · 2026-05-12 00:00:09#3 · $354 · 2026-05-12 01:00:09#4 · $354 · 2026-05-12 02:00:11
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#4 2026-05-12 02:00:11 48.4 48.4 $354 46.8 39.5 58.9 75.4
#3 2026-05-12 01:00:09 48.4 48.4 $354 46.8 39.5 58.9 75.4
#2 2026-05-12 00:00:09 48.4 48.4 $354 46.8 39.5 58.9 75.4
#1 2026-05-11 23:17:33 48.4 48.4 $354 46.8 39.5 58.9 75.4