Unverified50% confidenceBenchmarkExact time
In 50 real issues from the SWE-Bench Verified benchmark, Saluki successfully resolved 30, while the original model resolved 33, retaining approximately 91% of real-world bug-fixing capability.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedIn the BFCL official 100-item parallel tool-calling test, Saluki scored 42, surpassing the original model's 35, representing approximately a 20% improvement in success rate.69% similarUnverifiedSaluki 27B surpasses the full-precision original model in tool-calling capability66% similarUnverifiedIn 120 function-calling tests on Underdog Bench 120—built on Berkeley's BFCL V4 leaderboard—Saluki 27B scored 88, surpassing the full-size original model's score of 84.64% similarUnverifiedSaluki scored 93.5 on the IFEval benchmark (versus the original model's 91.5), and scored 72.7 on IFBench, surpassing the original model's 71.0.60% similarUnverifiedMuse Glimmer 30B scored 51.2 on the SWE benchmark, meaning it can solve approximately half of real-world software engineering problems.56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1000725API
curl https://kongchang.com/api/v1/knowledge/claims/1000725MCP
get_claim(id=1000725)