MDL
Qwen2.5-Coder-14B-Instruct
Qwen
Parameters
14B
Downloads
3.9M
on HF
Likes
172
Avg score
32.1
6 benchmarks
Weights
Open
Released
Nov 6, 2024
About
Qwen2.5-Coder-14B-Instruct is a 14B-parameter open-weights model in the Qwen2 family from Qwen. Benchmarked on 6 evals, averaging 32.1.
apache-2.0text-generation
Benchmark scores · 6
avg 32.1 — higher is betterThe research behind this model
all papers mentioning it →Qwen2.5-Coder Technical ReportYaRN: Efficient Context Window Extension of Large Language ModelsQwen2 Technical ReportFPMoE: A Sparse Mixture-of-Experts Approach to Functional Code GenerationMay 27, 2026Beyond Inference-Time Search: Reinforcement Learning Synthesizes Reusable SolversMay 18, 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.