Coverage (30d)
18vs0
This Week
3vs0
Evidence
1 articlesRelationships
1Timeline
GPT-5.32026-04-18
Achieved 78.5% score on SWE-Bench coding benchmark
GPT-5.32026-04-16
Observed autonomously optimizing an embedding model for Qualcomm NPU for three hours.
GPT-5.32026-03-26
Achieved 100% resident identification accuracy in a safety evaluation for a care home smart speaker system.
GPT-5.32026-03-07
Released as OpenAI's most capable frontier model with unified coding, reasoning, and computer operation capabilities
GPT-5.32026-03-06
Demonstrated surpassing human baselines on OSWorld benchmark with 75% score
GPT-5.32026-03-05
OpenAI releases GPT-5.4 with native computer use, tool search, and 1M token context window
Evolver2026-02-28
Achieved 95% accuracy on ARC-AGI-2 benchmark
Ecosystem
GPT-5.3
developedOpenAI5 src
developed byOpenAI3 src
usesRetrieval-Augmented Generation1 src
competes withClaude Sonnet 4.61 src
competes withGemini 3 Flash1 src
competes withClaude AI1 src
Evolver
competes withGPT-5.31 src
usesARC-AGI-21 src
Benchmarks
gpqa
GPT-5.392
Evolver—
swe bench pro
GPT-5.356.8
Evolver—