AI Paper Atlas

Research map / Benchmarks / OBQA

OBQA leaderboard

23 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on OBQA. Best accuracy: 89.6 (LoRA + GNP, AAAI 2024).

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.

OBQA · accuracy

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

#accuracy ↑MethodPaperTopic
189.6LoRA + GNP
FLAN-T5 xxlarge (11B)
Graph Neural Prompting with Large Language Models
AAAI 2024 · Table 1
Retrieval and knowledge
288.8ETN
Llama-3.1-8B
Evidential Transformation Network: Turning Pretrained Models into Evidential Models for Post-hoc Uncertainty Estimation
CVPR 2026 · Table 2
Uncertainty and Gaussian processes
388.2InfoSteer intervention
Gemma-2-9B
Steering Information Utility in Key-Value Memory for Language Model Post-Training
NeurIPS 2025 · Table 1
Instruction and fine-tuning
487.8BLoB-Mean + TFB
Llama3.1-8B
Training-Free Bayesianization for Low-Rank Adapters of Large Language Models
NeurIPS 2025 · Table 1
Uncertainty and Gaussian processes
586.4LoRA-DA
LLaMA 2-7B
LoRA-DA: Data-Aware Initialization for Low-Rank Adaptation via Asymptotic Analysis
ICML 2026 · Table 1
Optimizers
685.5GraphVis
LLaVA-v1.6-Mistral (7B)
GraphVis: Boosting LLMs with Visual Knowledge Graph Integration
NeurIPS 2024 · Table 1
Multimodal LLMs
785KnowProxy
Llama-3.2-3B + Llama-3.2-1B proxy
KnowProxy: Adapting Large Language Models by Knowledge-guided Proxy
ICLR 2026 · Table 4
Instruction and fine-tuning
881.8EDFM
LLaMA-2-7B
Ensemble Distribution Distillation via Flow Matching
ICML 2025 · Table 5
Knowledge distillation
981.52BLoB (N=10)
Llama2-7B
BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models
NeurIPS 2024 · Table 1
Instruction and fine-tuning
1080D-LLM
LLaMA2-7B
D-LLM: A Token Adaptive Computing Resource Allocation Strategy for Large Language Models
NeurIPS 2024 · Table 1
Reasoning and chain of thought
13 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.