MDL
Qwen3.5 9B
Alibaba
Verified against Artificial Analysis · Jul 13, 2026
Capability
72
percentile index
Price /M
$0.1 / $0.15
in / out
Context
262.1K
tokens
Avg score
51.2
7 benchmarks
AA Intelligence
21.4
index
Speed
57 tok/s
TTFT 1.3s
Released
Mar 2, 2026
About
Qwen3.5 9B is a open-weights model in the Qwen3.5 family from Alibaba. Benchmarked on 7 evals, averaging 51.2.
Benchmark scores · 7
avg 51.2 — higher is betterThe research behind this model
all papers mentioning it →Dockerless: Environment-Free Program Verifier for Coding Agents▲ 109 on HF · Jun 26, 2026Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games▲ 48 on HF · Jun 17, 2026Multi-Turn Agentic Scientific Literature Search via Workflow Induction▲ 28 on HF · Jul 1, 2026LoMo: Local Modality Substitution for Deeper Vision-Language Fusion▲ 23 on HF · May 28, 2026Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents▲ 21 on HF · May 28, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.
Performance & price
Output speed57 tok/s
Latency (TTFT)1.3s
First answer37s
Price in / out$0.1 / $0.15 per 1M
Blended price$0.113 / 1M
Coding index28.7
Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →
History
full ledger →Capability over time
Append-only ledger — every observed change to this model's numbers.
API providers
Artificial Analysis$0.15/M