Unverified50% confidenceFactExact time
According to official statements, Ripple-65B Preview's score on Terminal-Bench 2.1 leads American open-source models with up to 15 times its parameter count.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
11/4/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 11/18/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedOn TerminalBench 4.0, Large 4 scores 41%, a 13-percentage-point improvement over the preview version from three weeks earlier, and Mistral says it ranks first among open-source models.59% similarUnverifiedA score of about 65% on Terminal-Bench is already above average, but comparisons across different versions (such as 4.0) require caution, because the task set and scoring rules may be adjusted.57% similarUnverifiedThe same DeepSeek v1.1 model scored between 69.8% and 74.2% on Terminal Bench 2.0 under different harnesses.55% similarUnverifiedFable 5.1 scored 52.6% on the Terminal Bench Science 0.1 benchmark, more than doubling the score of its previous generation.55% similarUnverifiedIn DeepSeek's official comparison, when running with the same checkpoint at best effort, its minimal framework scored 72.6 while the open-source code scored 65.5.54% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1137480API
curl https://kongchang.com/api/v1/knowledge/claims/1137480MCP
get_claim(id=1137480)