Expired50% confidenceFactTime unknown
Gemini 3.1 Pro's ranking on Live Code Bench is at the highest level in the industry
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
Gemini 3.5 Pro Leak Analysis: Coding Matches GPT 5.5, Spark Agent Sparks Privacy Controversy
bilibiliAI全文总结
Related Claims
UnverifiedGemini 3.0 Pro performs strongly on multiple programming benchmarks including Terminal Bench and Live Code Bench.81% similarUnverifiedGemini 3.1 Pro scored 54.2 on SWE Bench Pro.76% similarUnverifiedGemini 3.1 Pro High achieved a pass rate of 84.17% on the SWE-bench test, ranking first, with 307,000 lines of code generated, a bug density of 614 per million lines of code, and 210 security issues per million lines of code.73% similarUnverifiedGemini 2.5 Pro has ranked at the top of the Chatbot Arena coding leaderboard on multiple occasions.72% similarUnverifiedGemini 2.5 Pro tops the AIDER leaderboard for coding model benchmarks70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/55659API
curl https://kongchang.com/api/v1/knowledge/claims/55659MCP
get_claim(id=55659)