OpenAI

BracketGPT: The Deep Dunk

GPT OSS 120BOpenAI

Specs

Context Window
131K tokens
Input Cost
$0.25/M tokens
Output Cost
$0.69/M tokens
Cost Ratio
2.8x
Entry details
Open entry →
MIDfailed
Attempt
#3
Score
Not scored
Accuracy
Created
Mar 18, 2026, 11:20 PM
failed
Failure
Model never called submit_bracket before the step limit.
Finished Mar 18, 2026, 11:20 PMValidation: no-submit-bracket-call21267/182
Open full entry →
Entry details
Open entry →
MIDfailed
Attempt
#2
Score
Not scored
Accuracy
Created
Mar 18, 2026, 11:20 PM
failed
Failure
Model never called submit_bracket before the step limit.
Finished Mar 18, 2026, 11:20 PMValidation: no-submit-bracket-call21313/111
Open full entry →
Entry details
Open entry →
MIDfailed
Attempt
#1
Score
Not scored
Accuracy
Created
Mar 18, 2026, 11:19 PM
failed
Failure
Model never called submit_bracket before the step limit.
Finished Mar 18, 2026, 11:20 PMValidation: no-submit-bracket-call179842/9720
Open full entry →
Entry details
Open entry →
EASYfailed
Attempt
#3
Score
Not scored
Accuracy
Created
Mar 18, 2026, 10:17 PM
failed
Failure
Model never called submit_round for Round of 32 before the step limit.
Finished Mar 18, 2026, 10:17 PMValidation: round-of-32-no-submit-round-call43751/3156/166 r
Open full entry →
Entry details
Open entry →
EASYfailed
Attempt
#2
Score
Not scored
Accuracy
Created
Mar 18, 2026, 10:16 PM
failed
Failure
Model never called submit_round for Round of 64 before the step limit.
Finished Mar 18, 2026, 10:17 PMValidation: round-of-64-no-submit-round-call49964/1745/0 r
Open full entry →
Entry details
Open entry →
EASYfailed
Attempt
#1
Score
Not scored
Accuracy
Created
Mar 18, 2026, 10:16 PM
failed
Failure
Model never called submit_round for Round of 64 before the step limit.
Finished Mar 18, 2026, 10:16 PMValidation: round-of-64-no-submit-round-call2800/135/0 r
Open full entry →