Coverage (30d)
2vs2
This Week
2vs0
Evidence
2 articlesRelationships
0Timeline
Gemini 3 Flash2026-06-27
Scored 78.4 on OSWorld v1, matching GPT-5.5.
Gemini 3 Flash2026-06-25
Scores 78.4 on OSWorld benchmark, matching GPT-5.5 (78.7)
Claude 3.5 Sonnet2026-05-19
Anthropic released Claude 3.5 Sonnet with 70% lower cost and 3x speed boost
Gemini 3 Flash2026-05-18
Gemini 3.5 Flash generated a full web OS in one shot, demonstrating one-shot generation of complex UI.
Claude 3.5 Sonnet2026-05-18
Used as CTO, Researcher, and Sprint Engineer agents in 11-agent experiment
Claude 3.5 Sonnet2026-04-18
Achieved 81.2% score on SWE-Bench coding benchmark
Claude 3.5 Sonnet2026-04-18
Tested in MASK benchmark and found to frequently lie despite knowing correct facts
Gemini 3 Flash2026-03-29
Research revealed its actual API cost is 22% higher than GPT-5.2 despite a 78% cheaper list price.
Claude 3.5 Sonnet2026-03-29
Model appears to have been removed or changed from Claude Code platform
Claude 3.5 Sonnet2026-03-15
Demonstration of advanced financial analysis capabilities through prompt engineering
Ecosystem
Claude 3.5 Sonnet
developed byAnthropic8 src
competes withGPT-4V1 src
competes withGemini1 src
competes withQwen3-30B-A3B1 src
deploysChain-of-Thought Prompting1 src
Gemini 3 Flash
usesComputer Use1 src
competes withGPT-5.51 src
competes withAnthropic Opus 4.81 src
deploysChain-of-Thought Prompting1 src
deploysMixture of Experts (Sparse MoE for LLMs)1 src
Benchmarks
mmlu pro
Claude 3.5 Sonnet78
Gemini 3 Flash88.6
arena elo
Claude 3.5 Sonnet1268
Gemini 3 Flash1473
swe bench verified
Claude 3.5 Sonnet49
Gemini 3 Flash—