Kimi K2 Thinking

kimi-k2-thinking · 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

42.2 40.2 #1 · 41.2 · 2026-05-11 23:17:33#2 · 41.2 · 2026-05-12 00:00:09#3 · 41.2 · 2026-05-12 01:00:09#4 · 41.2 · 2026-05-12 02:00:11

Cost over time

$309 $307 #1 · $308 · 2026-05-11 23:17:33#2 · $308 · 2026-05-12 00:00:09#3 · $308 · 2026-05-12 01:00:09#4 · $308 · 2026-05-12 02:00:11
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#4 2026-05-12 02:00:11 41.2 41.2 $308 40.9 34.8 47.9 -
#3 2026-05-12 01:00:09 41.2 41.2 $308 40.9 34.8 47.9 -
#2 2026-05-12 00:00:09 41.2 41.2 $308 40.9 34.8 47.9 -
#1 2026-05-11 23:17:33 41.2 41.2 $308 40.9 34.8 47.9 -