Coverage (30d)
15vs4
This Week
3vs1
Evidence
2 articlesRelationships
1Timeline
Gemini 3 Flash2026-03-29
Research revealed its actual API cost is 22% higher than GPT-5.2 despite a 78% cheaper list price.
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
GPT-5.32026-03-01
Expected to follow shortly after DeepSeek v4 release
GPT-5.32026-02-28
Identified as experiencing up to 33% accuracy degradation in extended conversations according to new research
Ecosystem
GPT-5.3
developed byOpenAI
developedOpenAI5 src
competes withClaude Sonnet 4.61 src
usesGPT-5.3-Codex1 src
usesGDPval1 src
usesPlaywright1 src
Gemini 3 Flash
No mapped relationships
Benchmarks
gpqa
GPT-5.392
Gemini 3 Flash—
swe bench pro
GPT-5.356.8
Gemini 3 Flash—
mmlu pro
GPT-5.3—
Gemini 3 Flash88.6
arena elo
GPT-5.3—
Gemini 3 Flash1473