Coverage (30d)
0vs4
This Week
0vs0
Evidence
1 articlesRelationships
2Timeline
Claude 3.5 Sonnet2026-05-19
Anthropic released Claude 3.5 Sonnet with 70% lower cost and 3x speed boost
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
Qwen3-30B-A3B2026-04-16
Achieved 73.4% on SWE-bench Verified, beating predecessor and competing with Claude 3.5 Sonnet on vision tasks
Claude 3.5 Sonnet2026-03-29
Model appears to have been removed or changed from Claude Code platform
Qwen3-30B-A3B2026-03-16
Achieved 79.6% invariant responses in semantic invariance testing, outperforming larger models up to 405B parameters.
Claude 3.5 Sonnet2026-03-15
Demonstration of advanced financial analysis capabilities through prompt engineering
Ecosystem
Qwen3-30B-A3B
competes withClaude 3.5 Sonnet1 src
competes withQwen 3.5 Medium1 src
Claude 3.5 Sonnet
developed byAnthropic8 src
competes withQwen3-30B-A3B1 src
competes withGPT-4V1 src
competes withGemini1 src
deploysChain-of-Thought Prompting1 src
Benchmarks
mmlu pro
Qwen3-30B-A3B—
Claude 3.5 Sonnet78
arena elo
Qwen3-30B-A3B—
Claude 3.5 Sonnet1268
swe bench verified
Qwen3-30B-A3B—
Claude 3.5 Sonnet49