Expired50% confidenceFactExact time
LFM2.5 improved by 19 and 23 points respectively over the previous generation in the BFCL-v3 and BFCL-v4 tool-calling evaluations.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
LFM2.5 Local Deployment Hands-On: An 8B Parameter Model That Outperforms GPT-o3s in Tool Calling
bilibiliAGI_Ananas6/1/2026
Related Claims
UnverifiedLFM2.5在多项基准测试中展现出与体量高达其4倍模型相当的竞争力63% similarUnverifiedIn guided mode, the average end-to-end accuracy increased from 28.6% to 33.7%, and the ambiguity detection F1 score increased from 45.3% to 64.9%63% similarUnverifiedQwen3.5 scored 28.7 on the HLE doctoral-level comprehensive question evaluation, while GPT-5.2 scored 35.5.63% similarUnverifiedGlimmer's intelligence index score of 35 surpasses Gemma 2 27B (30) and nearly matches Qwen 2.5 (36), with Qwen 2.5 72B topping the leaderboard at 38.62% similarUnverifiedOmniMerge V4 achieved 73.4% on the MBPP code test, an improvement of 15.8 percentage points compared to the original Q6K quantization's 56.2%.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/49057API
curl https://kongchang.com/api/v1/knowledge/claims/49057MCP
get_claim(id=49057)