Claude 4 Sonnet (Reasoning)

claude-4-sonnet-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

39.6 37.6 #1 · 38.6 · 2026-05-11 23:17:33#2 · 38.6 · 2026-05-12 00:00:09#3 · 38.6 · 2026-05-12 01:00:09#4 · 38.6 · 2026-05-12 02:00:11

Cost over time

$1,347 $1,345 #1 · $1,346 · 2026-05-11 23:17:33#2 · $1,346 · 2026-05-12 00:00:09#3 · $1,346 · 2026-05-12 01:00:09#4 · $1,346 · 2026-05-12 02:00:11
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#4 2026-05-12 02:00:11 38.6 38.6 $1,346 38.7 34.1 43.0 61.8
#3 2026-05-12 01:00:09 38.6 38.6 $1,346 38.7 34.1 43.0 61.8
#2 2026-05-12 00:00:09 38.6 38.6 $1,346 38.7 34.1 43.0 61.8
#1 2026-05-11 23:17:33 38.6 38.6 $1,346 38.7 34.1 43.0 61.8