Coverage (30d)
9vs5
This Week
2vs0
Evidence
1 articlesRelationships
1Timeline
GPT-5.6 Sol2026-07-30
GPT-5.6 Sol scores 38.3% on ARC-AGI-3 with custom API, sparking benchmark fairness debate
GPT-5.6 Sol2026-07-25
GPT-5.6 Sol scored 72.7% on DeepSWE benchmark
GPT-5.6 Sol2026-07-14
GPT-5.6 Sol, Terra, and Luna launched on Amazon Bedrock
GPT-5.52026-06-12
Open-source MoE model matches GPT-5.5 on agentic coding benchmarks
GPT-5.52026-06-01
GPT-5.5 achieves 16% Pass@8 on MA-ProofBench Level I and 5% on Level II, outperforming most models.
Ecosystem
GPT-5.6 Sol
developedGPT-55 src
developedTerminal-Bench 2.13 src
competes withOpus 52 src
competes withClaude Fable 52 src
competes withGPT-5.51 src
usesOpenAI Codex1 src
GPT-5.5
developedGPT-55 src
developedAnthropic3 src
developedDeepSeek3 src
Benchmarks
arc agi 3
GPT-5.6 Sol7.8
GPT-5.5—
osworld
GPT-5.6 Sol—
GPT-5.578.4