Qwen3.5-9B
Qwen3.5-9B improved Pass@1 on SWE-bench Verified from 41.8% to 56.4%. The Decoder published an article discussing Qwen3.5‑9B’s fine‑tuning results. Qwen3.5‑9B was evaluated in the same study on AI model honesty as Opus 4.8. The Decoder featured Qwen3.5‑9B’s fine‑tuning results in its coverage. The Decoder published an article covering Qwen3.5‑9B’s fine‑tuned performance. Flora employs a 9B Qwen 3.5 model to split videos into action segments OpenCode uses the Qwen3.5 9B model Ollama runs the Qwen3.5 9B model· Entity summary generated by Graphiti
Relation timeline
BY VALID-FROM DATE- OpenCodeUSES MODELQwen3.5-9B
OpenCode uses the Qwen3.5 9B model
- OllamaRUNS MODELQwen3.5-9B
Ollama runs the Qwen3.5 9B model
- FloraHAS MODELQwen3.5-9B
Flora employs a 9B Qwen 3.5 model to split videos into action segments
- Qwen3.5-9BFEATURED INTHE DECODER
The Decoder featured Qwen3.5‑9B’s fine‑tuning results in its coverage.
- Qwen3.5-9BPUBLISHED ARTICLE CONCERNINGTHE DECODER
The Decoder published an article discussing Qwen3.5‑9B’s fine‑tuning results.
- Qwen3.5-9BPUBLISHED ARTICLE CONCERNINGTHE DECODER
The Decoder published an article covering Qwen3.5‑9B’s fine‑tuned performance.
- Qwen3.5-9BEVALUATED IN SAME STUDYOpus 4.8
Qwen3.5‑9B was evaluated in the same study on AI model honesty as Opus 4.8.
- Qwen3.5-9BINCREASED PASS AT 1 ON SWE BENCH VERIFIED FROM 41.8 TO 56.4SWE-bench Verified
Qwen3.5-9B improved Pass@1 on SWE-bench Verified from 41.8% to 56.4%.
Relations are facts Graphiti extracted from reports, not verbatim quotes. An end date means later reporting showed the relation no longer holds.
Events 3
- Coding From the Himalayas With an Offline AI Agent1 cited report · 2026-10-27
- Nvidia open-sources Flora to make robot video labeling 125x cheaper than GPT-6 Astra1 cited report · 2026-10-25
- AI models hide mistakes in their own work reports, but one sentence in your prompt can help1 cited report · 2026-10-17
Source reports 4
- Coding From the Himalayas With an Offline AI AgentLatent Space · 2026-10-27
- Nvidia open-sources Flora to make robot video labeling 125x cheaper than GPT-6 AstraThe Decoder · 2026-10-25
- AI models hide mistakes in their own work reports, but one sentence in your prompt can helpThe Decoder · 2026-10-17
- Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real HarnessesMicrosoft Research · first-party · 2026-10-08