o3-mini (High)

o3-mini-high · 34 samples · intelligence / 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

10.810.911.011.111.210-26 17:0010-27 01:1510-27 09:3010-27 17:4510-28 02:00 Run #3245 · Score · X: 2026-10-26 17:00:28 · Y: 11.0Run #3246 · Score · X: 2026-10-26 18:00:27 · Y: 11.0Run #3247 · Score · X: 2026-10-26 19:00:25 · Y: 11.0Run #3248 · Score · X: 2026-10-26 20:00:28 · Y: 11.0Run #3249 · Score · X: 2026-10-26 21:00:27 · Y: 11.0Run #3250 · Score · X: 2026-10-26 22:00:26 · Y: 11.0Run #3251 · Score · X: 2026-10-26 23:00:26 · Y: 11.0Run #3252 · Score · X: 2026-10-27 00:00:24 · Y: 11.0Run #3253 · Score · X: 2026-10-27 01:00:24 · Y: 11.0Run #3254 · Score · X: 2026-10-27 02:00:26 · Y: 11.0Run #3255 · Score · X: 2026-10-27 03:00:26 · Y: 11.0Run #3256 · Score · X: 2026-10-27 04:00:25 · Y: 11.0Run #3257 · Score · X: 2026-10-27 05:00:26 · Y: 11.0Run #3258 · Score · X: 2026-10-27 06:00:24 · Y: 11.0Run #3259 · Score · X: 2026-10-27 07:00:25 · Y: 11.0Run #3260 · Score · X: 2026-10-27 08:00:24 · Y: 11.0Run #3261 · Score · X: 2026-10-27 09:00:24 · Y: 11.0Run #3262 · Score · X: 2026-10-27 10:00:27 · Y: 11.0Run #3263 · Score · X: 2026-10-27 11:00:26 · Y: 11.0Run #3264 · Score · X: 2026-10-27 12:00:25 · Y: 11.0Run #3265 · Score · X: 2026-10-27 13:00:25 · Y: 11.0Run #3266 · Score · X: 2026-10-27 14:00:26 · Y: 11.0Run #3267 · Score · X: 2026-10-27 15:00:27 · Y: 11.0Run #3268 · Score · X: 2026-10-27 16:00:25 · Y: 11.0Run #3269 · Score · X: 2026-10-27 17:00:26 · Y: 11.0Run #3270 · Score · X: 2026-10-27 18:00:24 · Y: 11.0Run #3271 · Score · X: 2026-10-27 19:00:26 · Y: 11.0Run #3272 · Score · X: 2026-10-27 20:00:26 · Y: 11.0Run #3273 · Score · X: 2026-10-27 21:00:25 · Y: 11.0Run #3274 · Score · X: 2026-10-27 22:00:23 · Y: 11.0Run #3275 · Score · X: 2026-10-27 23:00:23 · Y: 11.0Run #3276 · Score · X: 2026-10-28 00:00:25 · Y: 11.0Run #3277 · Score · X: 2026-10-28 01:00:25 · Y: 11.0Run #3278 · Score · X: 2026-10-28 02:00:25 · Y: 11.0

Cost per task over time

$0.115$0.117$0.118$0.119$0.12010-26 17:0010-27 01:1510-27 09:3010-27 17:4510-28 02:00 Run #3245 · Cost per task · X: 2026-10-26 17:00:28 · Y: $0.115Run #3246 · Cost per task · X: 2026-10-26 18:00:27 · Y: $0.115Run #3247 · Cost per task · X: 2026-10-26 19:00:25 · Y: $0.115Run #3248 · Cost per task · X: 2026-10-26 20:00:28 · Y: $0.115Run #3249 · Cost per task · X: 2026-10-26 21:00:27 · Y: $0.115Run #3250 · Cost per task · X: 2026-10-26 22:00:26 · Y: $0.115Run #3251 · Cost per task · X: 2026-10-26 23:00:26 · Y: $0.120Run #3252 · Cost per task · X: 2026-10-27 00:00:24 · Y: $0.120Run #3253 · Cost per task · X: 2026-10-27 01:00:24 · Y: $0.120Run #3254 · Cost per task · X: 2026-10-27 02:00:26 · Y: $0.120Run #3255 · Cost per task · X: 2026-10-27 03:00:26 · Y: $0.120Run #3256 · Cost per task · X: 2026-10-27 04:00:25 · Y: $0.120Run #3257 · Cost per task · X: 2026-10-27 05:00:26 · Y: $0.120Run #3258 · Cost per task · X: 2026-10-27 06:00:24 · Y: $0.120Run #3259 · Cost per task · X: 2026-10-27 07:00:25 · Y: $0.120Run #3260 · Cost per task · X: 2026-10-27 08:00:24 · Y: $0.120Run #3261 · Cost per task · X: 2026-10-27 09:00:24 · Y: $0.120Run #3262 · Cost per task · X: 2026-10-27 10:00:27 · Y: $0.120Run #3263 · Cost per task · X: 2026-10-27 11:00:26 · Y: $0.120Run #3264 · Cost per task · X: 2026-10-27 12:00:25 · Y: $0.120Run #3265 · Cost per task · X: 2026-10-27 13:00:25 · Y: $0.120Run #3266 · Cost per task · X: 2026-10-27 14:00:26 · Y: $0.120Run #3267 · Cost per task · X: 2026-10-27 15:00:27 · Y: $0.120Run #3268 · Cost per task · X: 2026-10-27 16:00:25 · Y: $0.120Run #3269 · Cost per task · X: 2026-10-27 17:00:26 · Y: $0.120Run #3270 · Cost per task · X: 2026-10-27 18:00:24 · Y: $0.120Run #3271 · Cost per task · X: 2026-10-27 19:00:26 · Y: $0.120Run #3272 · Cost per task · X: 2026-10-27 20:00:26 · Y: $0.120Run #3273 · Cost per task · X: 2026-10-27 21:00:25 · Y: $0.120Run #3274 · Cost per task · X: 2026-10-27 22:00:23 · Y: $0.120Run #3275 · Cost per task · X: 2026-10-27 23:00:23 · Y: $0.120Run #3276 · Cost per task · X: 2026-10-28 00:00:25 · Y: $0.120Run #3277 · Cost per task · X: 2026-10-28 01:00:25 · Y: $0.120Run #3278 · Cost per task · X: 2026-10-28 02:00:25 · Y: $0.120

Time per task over time

1.04m1.09m1.14m1.19m1.24m10-26 17:0010-27 01:1510-27 09:3010-27 17:4510-28 02:00 Run #3245 · Time per task · X: 2026-10-26 17:00:28 · Y: 1.24mRun #3246 · Time per task · X: 2026-10-26 18:00:27 · Y: 1.24mRun #3253 · Time per task · X: 2026-10-27 01:00:24 · Y: 1.14mRun #3254 · Time per task · X: 2026-10-27 02:00:26 · Y: 1.14mRun #3255 · Time per task · X: 2026-10-27 03:00:26 · Y: 1.14mRun #3256 · Time per task · X: 2026-10-27 04:00:25 · Y: 1.14mRun #3257 · Time per task · X: 2026-10-27 05:00:26 · Y: 1.14mRun #3258 · Time per task · X: 2026-10-27 06:00:24 · Y: 1.14mRun #3259 · Time per task · X: 2026-10-27 07:00:25 · Y: 1.11mRun #3260 · Time per task · X: 2026-10-27 08:00:24 · Y: 1.11mRun #3261 · Time per task · X: 2026-10-27 09:00:24 · Y: 1.11mRun #3262 · Time per task · X: 2026-10-27 10:00:27 · Y: 1.14mRun #3263 · Time per task · X: 2026-10-27 11:00:26 · Y: 1.14mRun #3264 · Time per task · X: 2026-10-27 12:00:25 · Y: 1.14mRun #3265 · Time per task · X: 2026-10-27 13:00:25 · Y: 1.14mRun #3266 · Time per task · X: 2026-10-27 14:00:26 · Y: 1.14mRun #3267 · Time per task · X: 2026-10-27 15:00:27 · Y: 1.14mRun #3268 · Time per task · X: 2026-10-27 16:00:25 · Y: 1.14mRun #3269 · Time per task · X: 2026-10-27 17:00:26 · Y: 1.11mRun #3270 · Time per task · X: 2026-10-27 18:00:24 · Y: 1.11mRun #3271 · Time per task · X: 2026-10-27 19:00:26 · Y: 1.11mRun #3272 · Time per task · X: 2026-10-27 20:00:26 · Y: 1.11mRun #3273 · Time per task · X: 2026-10-27 21:00:25 · Y: 1.04mRun #3274 · Time per task · X: 2026-10-27 22:00:23 · Y: 1.04mRun #3275 · Time per task · X: 2026-10-27 23:00:23 · Y: 1.04mRun #3276 · Time per task · X: 2026-10-28 00:00:25 · Y: 1.04mRun #3277 · Time per task · X: 2026-10-28 01:00:25 · Y: 1.04mRun #3278 · Time per task · X: 2026-10-28 02:00:25 · Y: 1.04m
Run?Fetched?Score?Quality?Cost/task?Time/task?Intel?Agent?MMMU%?
#3278 2026-10-28 02:00:25 11.0 11.0 $0.120 1.04m 11.0 - -
#3277 2026-10-28 01:00:25 11.0 11.0 $0.120 1.04m 11.0 - -
#3276 2026-10-28 00:00:25 11.0 11.0 $0.120 1.04m 11.0 - -
#3275 2026-10-27 23:00:23 11.0 11.0 $0.120 1.04m 11.0 - -
#3274 2026-10-27 22:00:23 11.0 11.0 $0.120 1.04m 11.0 - -
#3273 2026-10-27 21:00:25 11.0 11.0 $0.120 1.04m 11.0 - -
#3272 2026-10-27 20:00:26 11.0 11.0 $0.120 1.11m 11.0 - -
#3271 2026-10-27 19:00:26 11.0 11.0 $0.120 1.11m 11.0 - -
#3270 2026-10-27 18:00:24 11.0 11.0 $0.120 1.11m 11.0 - -
#3269 2026-10-27 17:00:26 11.0 11.0 $0.120 1.11m 11.0 - -
#3268 2026-10-27 16:00:25 11.0 11.0 $0.120 1.14m 11.0 - -
#3267 2026-10-27 15:00:27 11.0 11.0 $0.120 1.14m 11.0 - -
#3266 2026-10-27 14:00:26 11.0 11.0 $0.120 1.14m 11.0 - -
#3265 2026-10-27 13:00:25 11.0 11.0 $0.120 1.14m 11.0 - -
#3264 2026-10-27 12:00:25 11.0 11.0 $0.120 1.14m 11.0 - -
#3263 2026-10-27 11:00:26 11.0 11.0 $0.120 1.14m 11.0 - -
#3262 2026-10-27 10:00:27 11.0 11.0 $0.120 1.14m 11.0 - -
#3261 2026-10-27 09:00:24 11.0 11.0 $0.120 1.11m 11.0 - -
#3260 2026-10-27 08:00:24 11.0 11.0 $0.120 1.11m 11.0 - -
#3259 2026-10-27 07:00:25 11.0 11.0 $0.120 1.11m 11.0 - -
#3258 2026-10-27 06:00:24 11.0 11.0 $0.120 1.14m 11.0 - -
#3257 2026-10-27 05:00:26 11.0 11.0 $0.120 1.14m 11.0 - -
#3256 2026-10-27 04:00:25 11.0 11.0 $0.120 1.14m 11.0 - -
#3255 2026-10-27 03:00:26 11.0 11.0 $0.120 1.14m 11.0 - -
#3254 2026-10-27 02:00:26 11.0 11.0 $0.120 1.14m 11.0 - -
#3253 2026-10-27 01:00:24 11.0 11.0 $0.120 1.14m 11.0 - -
#3252 2026-10-27 00:00:24 11.0 11.0 $0.120 - 11.0 - -
#3251 2026-10-26 23:00:26 11.0 11.0 $0.120 - 11.0 - -
#3250 2026-10-26 22:00:26 11.0 11.0 $0.115 - 11.0 - -
#3249 2026-10-26 21:00:27 11.0 11.0 $0.115 - 11.0 - -
#3248 2026-10-26 20:00:28 11.0 11.0 $0.115 - 11.0 - -
#3247 2026-10-26 19:00:25 11.0 11.0 $0.115 - 11.0 - -
#3246 2026-10-26 18:00:27 11.0 11.0 $0.115 1.24m 11.0 - -
#3245 2026-10-26 17:00:28 11.0 11.0 $0.115 1.24m 11.0 - -