OpenCodePapers

multimodal-reasoning-on-babyvision

Visual ReasoningMultimodal Reasoning
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeAccuracyModelNameReleaseDate
GLM-5.3-Flash: Frontier Intelligence, Flash Cost✓ Link53.4GLM-5.3-Flash2026-08-26
Qwen3.5: Towards Native Multimodal Agents✓ Link52.3Qwen3.5-397B-A17B2026-02-16
dots3-note Preview: A Small but Mighty Step Toward Long-Horizon Agency in Real Life✓ Link50dots3-note Preview2026-08-13
Qwen3.5: Towards Native Multimodal Agents✓ Link44.6Qwen3.5-27B2026-02-16
Qwen3.5: Towards Native Multimodal Agents✓ Link40.2Qwen3.5-122B-A10B2026-02-16
Kimi K2.6✓ Link39.8Kimi K2.62026-04-20
Qwen3.5: Towards Native Multimodal Agents✓ Link38.4Qwen3.5-35B-A3B2026-02-16
Kimi K2.5: Visual Agentic Intelligence✓ Link36.5Kimi K2.52026-02-02
HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning32.22Qwen3.5-397B-A17B (RLVR w/ Multi-Hop)2026-03-17
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture✓ Link31.70SenseNova-U1-A3B-MoT2026-05-12
EXAONE 4.5 Technical Report✓ Link18.8EXAONE 4.5 (Reasoning)2026-04-09
LongCat-Next: Lexicalizing Modalities as Discrete Tokens✓ Link14.4LongCat-Next (A3B, 68.5B)2026-03-29
LoopVL: Recurrent Visual Intelligence✓ Link13.14LoopVL-1B2026-09-29
Check out how to contribute new results. Then edit this file on GitLab or GitHub.