Expired50% confidenceEventExact time
Kimi 5.1 was the first model to finish its code output in the first round but threw errors immediately upon execution
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
AI Coding Showdown: Four Major Models Show Shocking Performance Gaps on a Dynamic Web Scraping Task
bilibili图动中国6/11/2026
Related Claims
UnverifiedIn the test, Kimi K2.6 spent over 22 minutes repeatedly retrying, all of which failed, and was unable to generate runnable code.67% similarUnverifiedIn front-end development tests, Kimi K2.6 surpassed Claude Opus 4 in certain scenarios.60% similarUnverifiedKimi K2.6 achieved a score of 58.6% on the SWE-Bench Pro benchmark, ranking first among open-source models.59% similarUnverifiedKimi K2.5 scored 96.1 on the AMM5 2025 comprehensive capability test and 87.6 on the GPQA Diamond high-difficulty question test.57% similarUnverifiedClaude Haiku 4.5 failed all 5 programming task tests56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/48435API
curl https://kongchang.com/api/v1/knowledge/claims/48435MCP
get_claim(id=48435)