MDL
GPT-5 nano
OpenAI
Verified against Artificial Analysis · Jul 13, 2026
Capability
72
percentile index
Price /M
$0.05 / $0.4
in / out
Context
400K
tokens
Avg score
51.1
10 benchmarks
AA Intelligence
19.9
index
Speed
163 tok/s
TTFT 1m 23s
Released
Aug 7, 2025
About
GPT-5 nano is a proprietary model in the GPT family from OpenAI. Benchmarked on 10 evals, averaging 51.1.
Benchmark scores · 10
avg 51.1 — higher is betterThe research behind this model
all papers mentioning it →Mind Your Tone: Does Tone Alter LLM Performance?May 27, 2026Models Can Model, But Can't Bind: Structured Grounding in Text-to-OptimizationMay 20, 2026Benchmarking EngGPT2-16B-A3B against Comparable Italian and International Open-source LLMsMay 8, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.
Performance & price
Output speed163 tok/s
Latency (TTFT)1m 23s
Price in / out$0.05 / $0.4 per 1M
Blended price$0.138 / 1M
Math index83.7
Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →
History
full ledger →Capability over time
Append-only ledger — every observed change to this model's numbers.
API providers
Artificial Analysis$0.4/M