OpenCodePapers

instruction-following-on-arena-hard-auto-v2

Natural Language UnderstandingInstruction Following
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeAccuracyModelNameReleaseDate
LongCat-Flash Technical Report✓ Link86.50LongCat-Flash2025-09-01
Qwen3-Next82.7Qwen3-Next-80B-A3B-Instruct2025-09-09
Unified Audio Intelligence Without Regressing on Text Intelligence81.6Audex 30B-A3B2026-07-06
Qwen3-VL Technical Report✓ Link77.4Qwen3-VL-235B-A22B-Instruct2025-11-26
Nanbeige4.1-3B: A Small General Model that Reasons, Aligns, and Acts✓ Link73.2Nanbeige4.1-3B2026-02-13
Nanbeige4-3B Technical Report: Exploring the Frontier of Small Language Models✓ Link60.0Nanbeige4-3B-Thinking-25112025-12-06