← Dashboard

GPT-5.4

OpenAI · GPT family · released 5 Mar 2026 · results from L2-Bench 1.0.0

GPT-5.4

84.0
L2-Bench overall score
Rank 2 of 9 on L2-Bench 1.0.0 · $0.030 per task · tested 1 May 2026

L2-Bench Score by Competency

Average score across tasks in each competency. Higher is better. Rank is among all 9 models on L2-Bench 1.0.0.

Every run

Each run is a fixed record: its score and cost never change after it is published. When a setting was tested more than once on a version, the latest run is the one on the dashboard.

TestedVersionScoreCost per taskPrice usedStatus
1 May 2026 L2-Bench 1.0.0 84.0 $0.030 price from 5 Mar 2026 On dashboard

Price

FromInput, per million tokensOutput, per million tokens
5 Mar 2026$2.50$15.00

Cost per task uses the price in force on the day each run was tested.