Intern-Decision open models (0.8B–4B) beat Jev on multimodal decision benchmarks
max_paperclips · x · 2026-09-30
ModelScope released Intern-Decision (0.8B/2B/4B) for multimodal structured decision-making:
- Average scores of 79.38 / 84.68 / 90.02 across seven decision benchmarks; Intern-Decision-4B surpasses Jev at 88.74 with better probability calibration
- Reported mean latency of 33.98 / 33.28 / 44.16 ms locally vs 109.70 ms for Jev in the same HF setup
- One forward pass answers multiple-choice, scoring, and yes/no questions with typed JSON and calibrated probability distributions
- Text states plus up to eight images enable routing, tool selection, scoring, and workflow control
- Apache 2.0, with Qwen3.5 upstream notices retained
More from coding & agent
- Models improving doesn't obsolete your agentic coding scaffolding, argues pushback on viral take — max_paperclips · 2026-09-30
- Building a Code Review Agent That Learns From Feedback With Groq and Hindsight — pasulabhavya · 2026-09-30
- Open-Dots, an open-source clone of OpenAI's Dots, hits 4,500 GitHub stars in 24 hours — matchaman11 · 2026-09-30
- Graphsub pitches in-memory graph DB for agent data: don't trust one AI corp with it all — arthurcolle · 2026-09-30
- Ex-Googler: AI agents can't write prod code yet, but what else fits a 60-minute interview? — prajdabre · 2026-09-30
- Open-Source Offline AI Speaking Coach Built With Ollama and faster-whisper — iamrishavraj1 · 2026-09-30