AI Paper Atlas

Research map / Benchmarks / ScienceQA

ScienceQA leaderboard

86 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on ScienceQA. Best accuracy: 97.5 (MMFineReason-8B (SFT+RL), NeurIPS 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

ScienceQA · accuracy

63 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
197.5MMFineReason-8B (SFT+RL)
Qwen3-VL-8B-Instruct
MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods
NeurIPS 2026 · Table 3
Multimodal LLMs
297.37FlyLoRA
Qwen-2.5-14B
FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts
NeurIPS 2025 · Qwen-2.5-14B single-task table
Mixture of experts
397.3LIRA-8B
InternVL2-8B
LIRA: Inferring Segmentation in Large Multi-modal Models with Local Interleaved Region Assistance
ICCV 2025 · Table 1
Multimodal LLMs
497LLaVA-UHD-v3
Qwen2-7B
NaVLM-PVC: Progressive Visual Compression for Efficient Native-Resolution Encoding in MLLMs
ECCV 2026 · Table 2
Multimodal LLMs
596.8SEED
Qwen3-4B-Base
SEED: Self-Speculative Decoding via Implicit Encoder–Decoder
NeurIPS 2026 · Table 1
Reasoning and chain of thought
696.2Manzano-30BMANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer
ICLR 2026 · Table 2
Multimodal LLMs
795.9Ours
Qwen2-VL-7B
Visual Enhanced Depth Scaling for Multimodal Latent Reasoning
NeurIPS 2026 · Table 1
Multimodal LLMs
895.2TVI-CoT
Qwen3-VL-8B
TVI-CoT: Text-Visual Interleaved Chain-of-Thought Reasoning for Multimodal Understanding
ICML 2026 · Table 1
Multimodal LLMs
995.14ReCoT
Mulberry-7B
ReCoT: Reflective Self-Correction Training for Mitigating Confirmation Bias in Large Vision-Language Models
ICCV 2025 · Table 1
Multimodal LLMs
1094.2RCTS
InternVL-2-8B
Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger
ICML 2025 · Table: Comparison results on r
Visual question answering
53 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

ScienceQA · score

24 papers, each with its best reported number for its own method; higher is better.

#score ↑MethodPaperTopic
194.3Saliency-R1-7B
Qwen2.5-VL-7B
Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Reward
CVPR 2026 · Table 2
Multimodal LLMs
293.5PACT
LLaVA-OneVision-7B
PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language Models
CVPR 2025 · Table 2
Attention and transformers
392.6SynerGen-VL
InternLM2-1.8B
SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding
CVPR 2025 · Table: visual question answeri
Multimodal LLMs
491.3UVU
Qwen2.5-3B-Instruct
UVU: Improving Multimodal Understanding via Vision-Language Unified Autoregressive Paradigm
CVPR 2026 · Table 4
Multimodal LLMs
590.3HiRes-LLaVA
Llama3.1-Ins-8B
HiRes-LLaVA: Restoring Fragmentation Input in High-Resolution Large Vision-Language Models
CVPR 2025 · Table: Quantitative results on
Multimodal LLMs
688.8UIO-2XLUnified-IO 2: Scaling Autoregressive Multimodal Models with Vision Language Audio and Action
CVPR 2024 · Table 5
Robot action and navigation
787.9VLM-R³
Qwen2.5-VL 7B
VLM-R³: Region Recognition, Reasoning, and Refinement for Enhanced Multimodal Chain-of-Thought
NeurIPS 2025 · Main Result table
Multimodal LLMs
879.54MuNG
Qwen2.5-VL-3B
Explore How to Inject Beneficial Noise in MLLMs
AAAI 2026 · Table 1
Multimodal LLMs
979.4UniGen
Qwen2.5-1.5B
UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generation
NeurIPS 2025 · Image understanding results ta
Multimodal LLMs
1078.5LEO
7B LLM
Rethinking the Mixture of Vision Encoders Paradigm for Enhanced Visual Understanding in Multimodal LLMs
NeurIPS 2026 · Table 4
Multimodal LLMs
14 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.