SOTAVerified

MMLU

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–75 of 340 papers

TitleStatusHype
Review-Instruct: A Review-Driven Multi-Turn Conversations Generation Method for Large Language ModelsCode0
Mining Hidden Thoughts from Texts: Evaluating Continual Pretraining with Synthetic Data for LLM Reasoning—0
KRISTEVA: Close Reading as a Novel Task for Benchmarking Interpretive Reasoning—0
AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection—0
SEM: Reinforcement Learning for Search-Efficient Large Language Models—0
A Scaling Law for Token Efficiency in LLM Fine-Tuning Under Fixed Compute Budgets—0
LLMs Outperform Experts on Challenging Biology Benchmarks—0
Elastic Weight Consolidation for Full-Parameter Continual Pre-Training of Gemma2—0
Measuring Hong Kong Massive Multi-Task Language Understanding—0
Memory-Efficient LLM Training by Various-Grained Low-Rank Projection of Gradients—0
ReasonIR: Training Retrievers for Reasoning TasksCode3
LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception—0
Video-MMLU: A Massive Multi-Discipline Lecture Understanding BenchmarkCode1
SHA256 at SemEval-2025 Task 4: Selective Amnesia -- Constrained Unlearning for Large Language Models via Knowledge IsolationCode0
DataDecide: How to Predict Best Pretraining Data with Small ExperimentsCode3
Transferable text data distillation by trajectory matching—0
Probing then Editing Response Personality of Large Language ModelsCode0
Domain-Adaptive Continued Pre-Training of Small Language Models—0
Large Language Models Could Be Rote Learners—0
Dynamic Cheatsheet: Test-Time Learning with Adaptive MemoryCode3
Task-Circuit Quantization: Leveraging Knowledge Localization and Interpretability for CompressionCode1
GAAPO: Genetic Algorithmic Applied to Prompt Optimization—0
Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning IncentivizationCode2
Sample, Don't Search: Rethinking Test-Time Alignment for Language Models—0
More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment—0
Show:102550
← PrevPage 3 of 14Next →
All datasetsSIOP 2020/2021MMLU-ProVCTK

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1go ahead, make my dataFinal_score61.72—Unverified
2#GreedyCowFinal_score61.63—Unverified
3Don't Ask Us yFinal_score61.4—Unverified
4Data_and_ConfusedFinal_score60.96—Unverified
5raakaFinal_score60.91—Unverified
6WafflesFinal_score60.91—Unverified
7Team ProcrustinationFinal_score60.64—Unverified
8Axiom Consulting PartnersFinal_score60.63—Unverified
9Lets_Be_FairFinal_score60.23—Unverified
10goonersFinal_score60.22—Unverified
#ModelMetricClaimedVerifiedStatus
1Orange-mini0-shot MRR99.19—Unverified
#ModelMetricClaimedVerifiedStatus
1HybridBeam+SI-SDRi13.3—Unverified