Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)

claude-sonnet-4-6-adaptive · 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

56.2 54.2 #1 · 55.2 · 2026-05-11 23:17:33#2 · 55.2 · 2026-05-12 00:00:09#3 · 55.2 · 2026-05-12 01:00:09#4 · 55.2 · 2026-05-12 02:00:11

Cost over time

$4,207 $4,205 #1 · $4,206 · 2026-05-11 23:17:33#2 · $4,206 · 2026-05-12 00:00:09#3 · $4,206 · 2026-05-12 01:00:09#4 · $4,206 · 2026-05-12 02:00:11
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#4 2026-05-12 02:00:11 55.2 55.2 $4,206 51.7 50.9 63.0 73.3
#3 2026-05-12 01:00:09 55.2 55.2 $4,206 51.7 50.9 63.0 73.3
#2 2026-05-12 00:00:09 55.2 55.2 $4,206 51.7 50.9 63.0 73.3
#1 2026-05-11 23:17:33 55.2 55.2 $4,206 51.7 50.9 63.0 73.3