Label Shift MonitorML & Forecasting
How each model performed on this task. Every chart states its N, and the reward carries a 95% confidence interval once there is more than one trial to measure.
Core metrics
Avg Cost
Mean API spend across trials; the line under a value is its observed range. N = 8 trials per model.
$1.09$0.87–$1.73
Fable-5high
$0.64$0.54–$0.77
Opus-4.8
$0.64$0.33–$1.06
GPT-5.4
$0.49$0.33–$0.69
Gemini-3
Extended metrics
Median Time
Wall-clock minutes, median across trials. N = 8 trials per model.
4m
GPT-5.4
3m
Opus-4.8
3m
Fable-5high
3m
Gemini-3
What the reward cost on this task
Reward vs Cost
Mean reward against mean spend per trial — top-left is more reward for less.
- Fable-5
- Opus-4.8
- Gemini-3
- GPT-5.4
$0.49Cost / trial$1.09