MDL
Qwen3 1.7B
Alibaba
Verified against Artificial Analysis · Jul 13, 2026
Capability
40
percentile index
Price /M
$0 / $0
in / out
Context
—
Avg score
28.5
11 benchmarks
AA Intelligence
2.6
index
Weights
Open
Released
Apr 28, 2025
About
Qwen3 1.7B is a open-weights model in the Qwen3 family from Alibaba. Benchmarked on 11 evals, averaging 28.5.
Benchmark scores · 11
avg 28.5 — higher is betterThe research behind this model
all papers mentioning it →Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE▲ 15 on HF · Jul 8, 2026Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR▲ 7 on HF · Jun 27, 2026ReNIO: Reweighting Negative Trajectory Importance for LLM On-Policy Distillation▲ 5 on HF · Jun 22, 2026Skill-Conditioned Gated Self-Distillation for LLM ReasoningMay 27, 2026Playing with Words, Improving with Rewards: Training Language Models for Creative AssociationMay 27, 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.
API providers
Artificial Analysis$0/M