Unverified60% confidenceBenchmarkExact time
d1-3B on text tasks: SQuAD 2.0 85.3, Civil Comments 93.0, MASSIVE intent 87.3, PubMedQA 66.0, BoolQ 86.7, XNLI 85.0, PAWS-X 76.9, averaging 82.9 across the seven.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
Unverifiedd1-3B averages 74.1 across 11 image benchmarks, versus 73.9 for LFM2.5-VL-3B; on VL-RewardBench d1-3B scores 65.0, far ahead of LFM2.5-VL-3B's 50.9, but it lags on CV-Bench (82.1 vs 87.6), VisualWebBench (71.4 vs 78.3), and POPE (88.5 vs 90.1).65% similarUnverifiedThe commits associated with this release include 0343bb1, 2b105fa, 125f493, and others.61% similarUnverifiedThe 4-bit LLaMA 3.1 8B dropped from 67.3 to 67.1 on the HumanEval coding benchmark.61% similarUnverifiedOfficial benchmark data shows that the new version of Qwen3 27B agent coding improved from 13.3 to 42.2, software engineering tasks improved from 49.3 to 79, and frontier agent tasks improved from 10.6 to 20.61% similarUnverifiedThe Top3 configuration achieved an accuracy of 97.148%, a weighted F1 of 97.055%, and an MCC of 0.9675, comprehensively outperforming the Full21 configuration using all 21 metrics (accuracy 95.999%, weighted F1 95.521%, MCC 0.9549).61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1005995API
curl https://kongchang.com/api/v1/knowledge/claims/1005995MCP
get_claim(id=1005995)