OpenCodePapers

multi-task-language-understanding-on-include

Natural Language UnderstandingMulti-task Language Understanding
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeAccuracyModelNameReleaseDate
Introducing Claude Opus 5✓ Link89.8Claude Opus 52026-07-24
Qwen3.5: Towards Native Multimodal Agents✓ Link85.6Qwen3.5-397B-A17B2026-02-16
Qwen3.5: Towards Native Multimodal Agents✓ Link82.8Qwen3.5-122B-A10B2026-02-16
Qwen3.5: Towards Native Multimodal Agents✓ Link81.6Qwen3.5-27B2026-02-16
Qwen3-VL Technical Report✓ Link80.0Qwen3-VL-235B-A22B-Thinking2025-11-26
Qwen3.5: Towards Native Multimodal Agents✓ Link79.7Qwen3.5-35B-A3B2026-02-16
Qwen3-Next78.9Qwen3-Next-80B-A3B-Instruct2025-09-09
Qwen3 Technical Report✓ Link78.7Qwen3-235B-A22B (Thinking)2025-05-14
Qwen3 Technical Report✓ Link75.6Qwen3-235B-A22B (Non-thinking)2025-05-14
Qwen3.5: Towards Native Multimodal Agents✓ Link75.6Qwen3.5-9B2026-02-16
Apertus: Democratizing Open and Compliant LLMs for Global Language Environments✓ Link58.2Apertus-70B-Instruct2025-09-17
Tiny Aya: Bridging Scale and Multilingual Depth✓ Link45.1Tiny Aya Global2026-03-12