#18
GPT-5.4
OpenAI · Proprietary · Reasoning · 1.05M context
67/ 100 composite
Released 2026-03-05
Benchmark Scores by Category
Coding
42.4
Knowledge
77.3
Reasoning
78.9
Agentic
74.7
Math
66.0
Multimodal
68.5
Scores based on weighted benchmarks: SWE-bench, LiveCodeBench (Coding); HLE, MMLU-Pro (Knowledge); ARC-AGI-2, LongBench v2 (Reasoning); Terminal-Bench, BrowseComp (Agentic); FrontierMath, AIME (Math).
API Pricing
Input
$2.5
per 1M tokens
Output
$15
per 1M tokens
Value Score
4.9
score per $1 output
Estimate Your Costs
Use our cost calculators to estimate monthly spend based on your specific workload: