Coverage (30d)
8vs10
This Week
4vs9
Evidence
1 articlesRelationships
1Timeline
GPT-3.52026-04-24
Early user review of GPT-5.5 in Codex highlights major improvements
GPT-3.52026-04-23
GPT-5.5 model family achieves leading position on Artificial Analysis Index for cost-performance
GPT-3.52026-04-23
GPT-5.5 spotted via Codex API backdoor, suggesting unofficial release channel for image generation.
GPT-3.52026-04-23
OpenAI engineer reveals GPT-5.5 is a Blackwell-native model trained on Nvidia GB200/GB300 NVL72 systems.
GPT-3.52026-04-23
Ethan Mollick announces early access to GPT-5.5, praises the Pro version, full writeup forthcoming.
GPT-3.52026-04-23
OpenAI announces GPT-5.5 as a new intelligence tier for agents and tool use
Gemini 3 Pro2026-04-16
Achieved top score on METR time horizon benchmark, handling 90-minute software tasks
Gemini 3 Pro2026-02-20
Achieved state-of-the-art status on most benchmarks according to preliminary evaluations
Ecosystem
Gemini 3 Pro
usesMMLU1 src
competes withGPT-4 Turbo1 src
competes withClaude 31 src
deploysChain-of-Thought Prompting1 src
deploysFlashAttention1 src
deploysGrouped-Query Attention (GQA)1 src
GPT-3.5
competes withMicrosoft Excel1 src
competes withClaude 3.5 Opus1 src
competes withClaude Opus 4.71 src
competes withGemini 3 Pro1 src
competes withGPT-5.31 src
competes withArtificial Analysis1 src
Benchmarks
mmlu pro
Gemini 3 Pro90.1
GPT-3.5—
arena elo
Gemini 3 Pro1485
GPT-3.5—
swe bench verified
Gemini 3 Pro80.6
GPT-3.5—