Claude 4 Sonnet (Reasoning)

claude-4-sonnet-thinking · 21 samples · combined / raw

Scoring

Choose the quality benchmark and final score formula for this model.

Cost adjustment

Tune formulas that account for Cost per Task.

Score over time

27.427.627.727.828.006-30 05:0007-01 01:0007-01 21:0007-02 17:0007-03 13:00 Run #766 · Score · X: 2026-06-30 05:00:59 · Y: 27.7Run #768 · Score · X: 2026-06-30 07:00:59 · Y: 27.7Run #769 · Score · X: 2026-06-30 08:01:00 · Y: 27.7Run #770 · Score · X: 2026-06-30 11:01:01 · Y: 27.7Run #772 · Score · X: 2026-06-30 20:00:56 · Y: 27.7Run #771 · Score · X: 2026-06-30 20:00:56 · Y: 27.7Run #776 · Score · X: 2026-07-01 03:00:59 · Y: 27.7Run #777 · Score · X: 2026-07-01 04:01:02 · Y: 27.7Run #780 · Score · X: 2026-07-01 09:01:00 · Y: 27.7Run #781 · Score · X: 2026-07-01 11:01:00 · Y: 27.7Run #784 · Score · X: 2026-07-01 20:01:00 · Y: 27.7Run #785 · Score · X: 2026-07-01 21:01:00 · Y: 27.7Run #788 · Score · X: 2026-07-02 01:01:00 · Y: 27.7Run #789 · Score · X: 2026-07-02 02:00:58 · Y: 27.7Run #792 · Score · X: 2026-07-02 05:00:59 · Y: 27.7Run #793 · Score · X: 2026-07-02 08:00:58 · Y: 27.7Run #796 · Score · X: 2026-07-02 12:00:49 · Y: 27.7Run #797 · Score · X: 2026-07-02 15:00:46 · Y: 27.7Run #801 · Score · X: 2026-07-03 08:00:45 · Y: 27.7Run #803 · Score · X: 2026-07-03 12:00:49 · Y: 27.7Run #804 · Score · X: 2026-07-03 13:00:47 · Y: 27.7

Cost per task over time

$1,044$1,054$1,063$1,073$1,08306-30 05:0007-01 01:0007-01 21:0007-02 17:0007-03 13:00 Run #766 · Cost per task · X: 2026-06-30 05:00:59 · Y: $1,044Run #768 · Cost per task · X: 2026-06-30 07:00:59 · Y: $1,044Run #769 · Cost per task · X: 2026-06-30 08:01:00 · Y: $1,044Run #770 · Cost per task · X: 2026-06-30 11:01:01 · Y: $1,044Run #772 · Cost per task · X: 2026-06-30 20:00:56 · Y: $1,044Run #771 · Cost per task · X: 2026-06-30 20:00:56 · Y: $1,044Run #776 · Cost per task · X: 2026-07-01 03:00:59 · Y: $1,044Run #777 · Cost per task · X: 2026-07-01 04:01:02 · Y: $1,044Run #780 · Cost per task · X: 2026-07-01 09:01:00 · Y: $1,044Run #781 · Cost per task · X: 2026-07-01 11:01:00 · Y: $1,044Run #784 · Cost per task · X: 2026-07-01 20:01:00 · Y: $1,044Run #785 · Cost per task · X: 2026-07-01 21:01:00 · Y: $1,044Run #788 · Cost per task · X: 2026-07-02 01:01:00 · Y: $1,044Run #789 · Cost per task · X: 2026-07-02 02:00:58 · Y: $1,044Run #792 · Cost per task · X: 2026-07-02 05:00:59 · Y: $1,044Run #793 · Cost per task · X: 2026-07-02 08:00:58 · Y: $1,044Run #796 · Cost per task · X: 2026-07-02 12:00:49 · Y: $1,044Run #797 · Cost per task · X: 2026-07-02 15:00:46 · Y: $1,044Run #801 · Cost per task · X: 2026-07-03 08:00:45 · Y: $1,083Run #803 · Cost per task · X: 2026-07-03 12:00:49 · Y: $1,083Run #804 · Cost per task · X: 2026-07-03 13:00:47 · Y: $1,083

Time per task over time

No chart data.

Run?Fetched?Score?Quality?Cost/task?Time/task?Intel?Code?Agent?MMMU%?
#804 2026-07-03 13:00:47 27.7 27.7 $1,083 - 28.9 37.6 16.6 61.8
#803 2026-07-03 12:00:49 27.7 27.7 $1,083 - 28.9 37.6 16.6 61.8
#801 2026-07-03 08:00:45 27.7 27.7 $1,083 - 28.9 37.6 16.6 61.8
#797 2026-07-02 15:00:46 27.7 27.7 $1,044 - 28.9 37.6 16.6 61.8
#796 2026-07-02 12:00:49 27.7 27.7 $1,044 - 28.9 37.6 16.6 61.8
#793 2026-07-02 08:00:58 27.7 27.7 $1,044 - 28.9 37.6 16.6 61.8
#792 2026-07-02 05:00:59 27.7 27.7 $1,044 - 28.9 37.6 16.6 61.8
#789 2026-07-02 02:00:58 27.7 27.7 $1,044 - 28.9 37.6 16.6 61.8
#788 2026-07-02 01:01:00 27.7 27.7 $1,044 - 28.9 37.6 16.6 61.8
#785 2026-07-01 21:01:00 27.7 27.7 $1,044 - 28.9 37.6 16.6 61.8
#784 2026-07-01 20:01:00 27.7 27.7 $1,044 - 28.9 37.6 16.6 61.8
#781 2026-07-01 11:01:00 27.7 27.7 $1,044 - 28.9 37.6 16.6 61.8
#780 2026-07-01 09:01:00 27.7 27.7 $1,044 - 28.9 37.6 16.6 61.8
#777 2026-07-01 04:01:02 27.7 27.7 $1,044 - 28.9 37.6 16.6 61.8
#776 2026-07-01 03:00:59 27.7 27.7 $1,044 - 28.9 37.6 16.6 61.8
#771 2026-06-30 20:00:56 27.7 27.7 $1,044 - 28.9 37.6 16.6 61.8
#772 2026-06-30 20:00:56 27.7 27.7 $1,044 - 28.9 37.6 16.6 61.8
#770 2026-06-30 11:01:01 27.7 27.7 $1,044 - 28.9 37.6 16.6 61.8
#769 2026-06-30 08:01:00 27.7 27.7 $1,044 - 28.9 37.6 16.6 61.8
#768 2026-06-30 07:00:59 27.7 27.7 $1,044 - 28.9 37.6 16.6 61.8
#766 2026-06-30 05:00:59 27.7 27.7 $1,044 - 28.9 37.6 16.6 61.8