A new open-source model, Tiel-Coder-35B-A3B, has been released, optimized for coding tasks and long conversations. It achieves strong performance on the SWE-bench-Live benchmark, fixing 12 out of 25 problems, which is comparable to Anthropic's Opus 4.6 medium model. While Tiel excels in coding and multi-turn dialogue, it is less proficient in trivia and general knowledge tasks, scoring lower on MMLU-Pro compared to other models in its class. AI
IMPACT Offers a new open-source option for agentic coding and long conversational tasks, potentially improving developer productivity.
RANK_REASON Release of a new open-source model with benchmark performance data. [lever_c_demoted from research: ic=1 ai=1.0]
Read on Hugging Face Trending Models →
- Claw-Eval
- MMLU-Pro
- Opus 4.6
- Ornith-1.5-35B-A3B
- Qwen3.6-35B-A3B
- Qwen3.8-27B
- Sonnet 5
- SWE-bench-Live
- Tiel-Coder-35B-A3B
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →