Expired75% confidenceFactTime unknown
Kimi K2.5's token usage is 50% higher than that of the second- and third-ranked Gemini and Claude small models.
1
Sources
75%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
Valid until: 8/29/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedIn the overall performance rankings, Kimi K2.5 scored 64%, placing fifth, with the top four being Gemini 3 Pro (100%), Claude Opus 4.5 Max (74%+), GLM 4.7 (65%), and GPT-5.2X (65%).77% similarUnverifiedKimi K2.6 achieved a score of 58.6% on the SWE-Bench Pro benchmark, ranking first among open-source models.70% similarUnverifiedThe performance gap between Kimi K2.6 and Claude on SWE-Bench is less than 1%, but the price difference is 7x (Kimi is $0.8 per million tokens, Claude is $5).70% similarUnverifiedOn the Diamond subset, Claude 3.0 Opus scored 5.2%, Gemini 1.5 Pro scored 4.7%, GPT-4o Mini scored 4.6%, and Kimi K2.6 scored 3.8%.68% similarUnverifiedIn Velse AI's latest rankings on April 23, Kimi K2.6 ranked first and DeepSeek V4 ranked second, with only a 0.07 percentage point difference between the two.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/14593API
curl https://kongchang.com/api/v1/knowledge/claims/14593MCP
get_claim(id=14593)