OpenAI
GPT-5 Nano (High)
Released 2025-08-07 · Context 400K · Data snapshot 2026-10-26
Overall score
40.5
Awaiting benchmarks (insufficient coverage)Benchmark coverage
19.2%
5 third-party benchmarks
Context window
400K
tokens
Input price
$0.05
Cache read $0.00
Output price
$0.40
per million tokens
Prices converted at snapshot-day rate (USD/CNY 6.6702)
Dimension performance
Human preference
51.0
Office
37.9
Above averageBelow averageAnchored at 50 (reference models’ average); every 15 points ≈ one standard deviation
Benchmark details
Coding1 items
Terminal-Bench21.8
Office2 items
Tax Eval v267.38
MedCode30.44
Knowledge1 items
MMLU-Pro76.07
Human preference1 items
LMArena Human Blind Votehigh1337.7738
Multiple reasoning tiers of the same benchmark take the best value; raw scores have different scales and are not comparable across benchmarks.