Unverified50% confidenceBenchmarkExact time
At the time of its release, Grok-3 claimed to be on par with Claude 3.5 Sonnet on certain programming benchmarks.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/20/2026
First Seen
Valid until: 11/18/2026
Sources
Related Claims
UnverifiedClaude Sonnet 3.5 achieved the ability to use computers safely65% similarUnverifiedThe Grok model series has undergone rapid iteration from Grok-1 to Grok-3, with Grok-3 performing excellently in mathematical reasoning and code generation.64% similarUnverifiedAI models supported by Cursor include Claude 3.5, Claude 3.7 Sonnet, Gemini, the GPT series, as well as Groq, DeepSeek, and others.63% similarUnverifiedGrok 4.6 and DeepSeek V4 Pro's official version were released on the same day.61% similarUnverifiedThe architectural details of Grok 4.5 have not been fully disclosed, and the article speculates it may adopt a Mixture of Experts (MoE) architecture.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/780129API
curl https://kongchang.com/api/v1/knowledge/claims/780129MCP
get_claim(id=780129)