HLE
52.1 score
AI Leaderboard · Proprietary
GPT-5.4 benchmarks, pricing, and ranking.
Rank #4AskClash overall score: 76.8
$2.50 / $15.0Input and output token price, when published. Context: 1.05M.
API/OAuthBilling and access path cached for this model row.
GPT-5.4 benchmark snapshot
AskClash combines public benchmark cells into a weighted percentile score and penalizes missing coverage so narrow rows do not dominate better-measured models.
Overall76.8
Benchmark cells14
Context1.05M
CreatorOpenAI
Public benchmark scores
Only benchmark columns with cached public values are shown here. Missing cells remain blank in the live table.
GPQA
92.8 score
MATH-500
99.0 score
SWE-Pro
57.7 score
Terminal-Bench
75.1 score
OSWorld
75.0 score
MCP Atlas
70.6 score
CharXiv
82.8 score
MMMU-Pro
82.1 score
ARC-AGI 2
73.3 score
Tau2
87.1 score
Related model comparisons
Use these links to compare nearby frontier and open-weight models from the same AI leaderboard data.
Related AI and tech coverage
Cached AskClash article matches that can provide release, provider, or market context around this model.
GPT 5.4 is a big step for Codex
On evaluating and understanding the frontier of agents, and why I still turn to Claude.
Our evaluation of OpenAI's GPT-5.5 cyber capabilities
Our evaluation of OpenAI's GPT-5.5 cyber capabilities Simon Willison’s Weblog Subscribe 30th April 2026 - Link Blog Our evaluation of OpenAI's GPT-5.5 cyber capabilities . The UK's AI Security Institute previously evaluated Claude Mythos : now they've evaluated GPT-5.5 for finding security vulnerability and found it to be comparable to Mythos, but unlike Mythos it's generally available right now. Posted 30th April 2026 at 11:03 pm Recent articles LLM 0.32a0 is a major backwards-compatible refact
OpenAI locks GPT-5.5-Cyber behind velvet rope despite slamming Anthropic for doing exactly that
OpenAI locks GPT-5.5-Cyber behind velvet rope • The Register The Register Home Page Search Search The Register Navigation Topics Security All Security Cyber-crime Patches Research CSO Off-Prem All Off-Prem Edge + IoT Channel PaaS + IaaS SaaS On-Prem All On-Prem Systems Storage Networks HPC Personal Tech Cx0 Public Sector Software All Software AI + ML Applications Databases DevOps OSes Virtualization Offbeat All Offbeat Columnists Science Geek's Guide BOFH Legal Bootnotes Site News About Us More
[AINews] OpenAI GPT-next disproves 80 year old Erdős planar unit distance problem for under $1000
Latent Space
Last cached leaderboard date: May 22, 2026. This model page is generated from the AskClash AI Leaderboard cache and linked from the live leaderboard.