OpenAI
GPT-5.4
Released 2026-03-05 · Context 1050K · Data snapshot 2026-10-26
Overall score
62.8
Awaiting benchmarks (insufficient coverage)Benchmark coverage
11.5%
3 third-party benchmarks
Context window
1050K
tokens
Input price
$2.50
Cache read $0.25
Output price
$15.00
per million tokens
OpenRouter usage
#105
57.3B tokens/day
Prices converted at snapshot-day rate (USD/CNY 6.6702)
Dimension performance
Human preference
66.3
Coding
62.3
Above averageBelow averageAnchored at 50 (reference models’ average); every 15 points ≈ one standard deviation
Benchmark details
Coding2 items
Terminal-Bench81.8
Vibe Code Bench48.47
Human preference1 items
LMArena Human Blind Vote1464.8232
Multiple reasoning tiers of the same benchmark take the best value; raw scores have different scales and are not comparable across benchmarks.