GPT-5.6 Sol (xhigh)

gpt-5-6-sol-xhigh · 7 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

62.062.362.662.963.218:0019:3021:0022:3000:00 Run #817 · Score · X: 2026-07-09 18:00:49 · Y: 62.6Run #818 · Score · X: 2026-07-09 19:00:45 · Y: 62.6Run #819 · Score · X: 2026-07-09 20:00:44 · Y: 62.6Run #820 · Score · X: 2026-07-09 21:00:43 · Y: 62.6Run #821 · Score · X: 2026-07-09 22:00:42 · Y: 62.6Run #822 · Score · X: 2026-07-09 23:00:41 · Y: 62.6Run #823 · Score · X: 2026-07-10 00:00:42 · Y: 62.6

Cost per task over time

$0.672$0.677$0.682$0.687$0.69218:0019:3021:0022:3000:00 Run #817 · Cost per task · X: 2026-07-09 18:00:49 · Y: $0.682Run #818 · Cost per task · X: 2026-07-09 19:00:45 · Y: $0.682Run #819 · Cost per task · X: 2026-07-09 20:00:44 · Y: $0.682Run #820 · Cost per task · X: 2026-07-09 21:00:43 · Y: $0.682Run #821 · Cost per task · X: 2026-07-09 22:00:42 · Y: $0.682Run #822 · Cost per task · X: 2026-07-09 23:00:41 · Y: $0.682Run #823 · Cost per task · X: 2026-07-10 00:00:42 · Y: $0.682

Time per task over time

No chart data.

Run?Fetched?Score?Quality?Cost/task?Time/task?Intel?Code?Agent?MMMU%?
#823 2026-07-10 00:00:42 62.6 62.6 $0.682 - 57.7 78.3 51.8 82.7
#822 2026-07-09 23:00:41 62.6 62.6 $0.682 - 57.7 78.3 51.8 82.7
#821 2026-07-09 22:00:42 62.6 62.6 $0.682 - 57.7 78.3 51.8 82.7
#820 2026-07-09 21:00:43 62.6 62.6 $0.682 - 57.7 78.3 51.8 82.7
#819 2026-07-09 20:00:44 62.6 62.6 $0.682 - 57.7 78.3 51.8 82.7
#818 2026-07-09 19:00:45 62.6 62.6 $0.682 - 57.7 78.3 51.8 82.7
#817 2026-07-09 18:00:49 62.6 62.6 $0.682 - 57.7 78.3 51.8 82.7