OpenCodePapers

multiple-choice-question-answering-mcqa-on-supergpqa

Question AnsweringMultiple Choice Question Answering (MCQA)
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeAccuracyModelNameReleaseDate
Efficient Agentic Reasoning Through Self-Regulated Simulative Planning✓ Link73.0SR 2 AM-v1.0-30B2026-05-21
Qwen3.5: Towards Native Multimodal Agents✓ Link70.4Qwen3.5-397B-A17B2026-02-16
Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity68.7Seed2.0 Pro2026-06-30
Qwen3.5: Towards Native Multimodal Agents✓ Link67.1Qwen3.5-122B-A10B2026-02-16
Qwen3.5-Omni Technical Report66.4Qwen3.5-Omni-Plus2026-04-21
Qwen3.6✓ Link66.0Qwen3.6-27B2026-04-21
Qwen3.5: Towards Native Multimodal Agents✓ Link65.6Qwen3.5-27B2026-02-16
Qwen3.6✓ Link64.7Qwen3.6-35B-A3B2026-04-21
Qwen3-VL Technical Report✓ Link64.3Qwen3-VL-235B-A22B-Thinking2025-11-26
Introducing efficiency focused "Thinking CAP" model series✓ Link64.0ThinkingCap-Qwen3.6-27B2026-07-06
Qwen3.5: Towards Native Multimodal Agents✓ Link63.4Qwen3.5-35B-A3B2026-02-16
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture✓ Link59.71SenseNova-U1-A3B-MoT2026-05-12
Qwen3-Next58.8Qwen3-Next-80B-A3B-Instruct2025-09-09
Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale✓ Link58.32Ling-2.6-1T2026-06-13
Qwen3.5: Towards Native Multimodal Agents✓ Link58.2Qwen3.5-9B2026-02-16
Qwen3-Coder-Next Technical Report✓ Link57.45Qwen3-Coder-Next2026-02-28
Kimi K2: Open Agentic Intelligence✓ Link57.2Kimi K22025-07-28
Nanbeige4-3B Technical Report: Exploring the Frontier of Small Language Models✓ Link53.2Nanbeige4-3B-Thinking-25112025-12-06
STEP3-VL-10B Technical Report✓ Link53.15Step3-VL-10B (PaCoRe)2026-01-14
On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability✓ Link51.36Qwen3.8-Flash-Next-Base2026-08-31
Data Science and Technology Towards AGI Part I: Tiered Data Management✓ Link40.8MiniCPM5-2B2026-02-09
MiniCPM5-2B✓ Link40.8MiniCPM5-2B2026-09-07
J-Zero: Unified Challenger--Solver--Judge Co-Evolution from Zero Data✓ Link33.22J-Zero-8B2026-08-27
Questioning the Questions: Sustaining Self-Evolution in Reasoning Models✓ Link29.4R-Quest (Qwen3-4B-Base)2026-10-03
MiniCPM5-1B✓ Link23.14MiniCPM5-1B (Thinking)2026-05-25