Claude 3 Haiku

claude-3-haiku · 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

9.7 7.7 #1 · 8.7 · 2026-05-11 23:17:33#2 · 8.7 · 2026-05-12 00:00:09#3 · 8.7 · 2026-05-12 01:00:09#4 · 8.7 · 2026-05-12 02:00:11

Cost over time

$37.4 $35.4 #1 · $36.4 · 2026-05-11 23:17:33#2 · $36.4 · 2026-05-12 00:00:09#3 · $36.4 · 2026-05-12 01:00:09#4 · $36.4 · 2026-05-12 02:00:11
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#4 2026-05-12 02:00:11 8.7 8.7 $36.4 12.3 6.7 7.0 30.8
#3 2026-05-12 01:00:09 8.7 8.7 $36.4 12.3 6.7 7.0 30.8
#2 2026-05-12 00:00:09 8.7 8.7 $36.4 12.3 6.7 7.0 30.8
#1 2026-05-11 23:17:33 8.7 8.7 $36.4 12.3 6.7 7.0 30.8