MDL
GPT-5.5
OpenAI
Verified against Artificial Analysis · Jul 13, 2026
Capability
97
percentile index
Price /M
$5 / $30
in / out
Context
1.1M
tokens
Avg score
71.2
7 benchmarks
AA Intelligence
54.8
index
Speed
72 tok/s
TTFT 25s
Released
Apr 23, 2026
About
GPT-5.5 is a proprietary model in the GPT family from OpenAI. Benchmarked on 7 evals, averaging 71.2.
Benchmark scores · 7
avg 71.2 — higher is betterThe research behind this model
all papers mentioning it →Toward Generalist Autonomous Research via Hypothesis-Tree Refinement▲ 115 on HF · Jun 10, 2026EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions▲ 79 on HF · Jun 22, 2026K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts▲ 55 on HF · Jun 1, 2026EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments▲ 50 on HF · Jul 2, 2026SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe▲ 29 on HF · Jul 3, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.
Performance & price
Output speed72 tok/s
Latency (TTFT)25s
Price in / out$5 / $30 per 1M
Blended price$11.25 / 1M
Coding index74.9
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$30/M