DeepSeek R1 0528 (May '25)

deepseek-r1 · 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

25.0 23.0 #1 · 24.0 · 2026-05-11 23:17:33#2 · 24.0 · 2026-05-12 00:00:09#3 · 24.0 · 2026-05-12 01:00:09#4 · 24.0 · 2026-05-12 02:00:11

Cost over time

$281 $279 #1 · $280 · 2026-05-11 23:17:33#2 · $280 · 2026-05-12 00:00:09#3 · $280 · 2026-05-12 01:00:09#4 · $280 · 2026-05-12 02:00:11
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#4 2026-05-12 02:00:11 24.0 24.0 $280 27.1 24.0 20.8 -
#3 2026-05-12 01:00:09 24.0 24.0 $280 27.1 24.0 20.8 -
#2 2026-05-12 00:00:09 24.0 24.0 $280 27.1 24.0 20.8 -
#1 2026-05-11 23:17:33 24.0 24.0 $280 27.1 24.0 20.8 -