MDL
Qwen2.5-14B
Qwen
Parameters
14B
Downloads
89.5K
on HF
Likes
153
Avg score
32.0
6 benchmarks
Weights
Open
Released
Sep 15, 2024
About
Qwen2.5-14B is a 14B-parameter open-weights model in the Qwen2 family from Qwen. Benchmarked on 6 evals, averaging 32.0.
apache-2.0text-generation
Benchmark scores · 6
avg 32.0 — higher is betterThe research behind this model
all papers mentioning it →Qwen2 Technical ReportQwen2.5-1M Technical Report8 cites · Jan 26, 2025MarginGate: Sparse Margin-Triggered Verification for Batch-Invariant LLM InferenceMay 28, 2026CONCAT: Consensus- and Confidence-Driven Ad Hoc Teaming for Efficient LLM-Based Multi-Agent SystemsMay 28, 2026When Do LLM Agents Treat Surface Noise Differently from Semantic Noise? A 68-Cell Measurement Study with a Held-Out Trace-Level ValidationMay 25, 2026ProActor: Timing-Aware Reinforcement Learning for Proactive Task Scheduling AgentsMay 24, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.
History
full ledger →Capability over time
Append-only ledger — every observed change to this model's numbers.