MDL
Qwen2.5-72B
Qwen
Parameters
72.7B
Downloads
—
Likes
—
Avg score
38.4
6 benchmarks
Weights
Open
Released
—
About
Qwen2.5-72B is a 72.7B-parameter open-weights model in the Qwen2 family from Qwen. Benchmarked on 6 evals, averaging 38.4.
other
Benchmark scores · 6
avg 38.4 — higher is betterThe research behind this model
all papers mentioning it →Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning▲ 7 on HF · Jun 1, 2026Qwen2.5 Technical Report71 cites · Dec 19, 2024FormalRewardBench: A Benchmark for Formal Theorem Proving Reward ModelsMay 11, 2026ReFlect: An Effective Harness System for Complex Long-Horizon LLM ReasoningMay 7, 2026Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and PerformanceJul 30, 2025
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.