Unverified50% confidenceBenchmarkExact time
Running as BLM, the open-source model Qwen3.8-27B raised its task solve rate on the τ²-bench telecom benchmark from 29% to 96%, with the number of model calls reduced by 93%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/20/2026
First Seen
Valid until: 1/18/2027
Sources
Related Entities
Related Claims
UnverifiedFor Claude Opus 5.5, which can already solve 96% of tasks on its own, running it in BLM mode reduced model calls and per-task cost by about 98% and additionally solved 2 tasks.66% similarUnverifiedAfter switching to Plan B, CPU usage for the same verification task dropped from approximately 70% to approximately 3%, a reduction of about 96%.64% similarUnverifiedOn the LSTM time-series prediction task, parameters were reduced from 12,051 to 2,048, with a validation set MSE as low as 0.00006.63% similarUnverifiedFine-tuned v3 achieved a safety recall of 13/21 (62%) at the 0.8 alert threshold, versus 0/21 for zero-shot; false alarms on ordinary chat dropped from 2.9% to 1.4%.62% similarUnverifiedCompared to its predecessor, ChatGPT 3.5 Turbo improved response speed by approximately 25% and reduced costs by 90%.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1074725API
curl https://kongchang.com/api/v1/knowledge/claims/1074725MCP
get_claim(id=1074725)