NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
446 results for “keyword:"benchmarks"” in ICLR 2027. 117 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]StreamArena: Toward Continuous, Interactive, and Long-Horizon Agentic Streaming Video Understanding▼5.8k2.33
[PDF]Benchmark Scores Are Pipeline-Dependent: A Reliability Audit of Cybersecurity LLM Benchmarks▲9.2k2.67
[PDF]ProdBench: Evaluating Requirement Recovery and Realization in Producer-oriented Software Development▲3.0k2.33
[PDF]When Reasoning Fails to Stop: Prompt-Induced Resource Exhaustion in Black-Box Reasoning Models▼1611.50
[PDF]PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents▼5.8k2.33
[PDF]Wiki Live Challenge: Challenging Deep Research Agents with Expert-Level Wikipedia Articles▼5.8k2.33
[PDF]GameLogicBench: Evaluating Coding Agents on Runtime Game Logic with Tick-Level State Assertions▼1.2k3.00
[PDF]HABIT-Bench: Evaluating Habit Induction from Longitudinal Weak Evidence in Agent Memory▲5.4k3.00
[PDF]SEA-Boundary: A Diagnostic Benchmark for State Preparation, Information Access, and Evidence Use in Long-Context LLM Systems▲5.4k3.00
[PDF]Generation and Judgment Diverge in Code Models: A Matched Benchmark with Derived Ground Truth▲3.9k1.67
[PDF]SegBench-GC: Testing Segmentation Invariance in Multi-Step Offline Goal-Conditioned Reinforcement Learning▼1.2k1.67
[PDF]ToolPlan-Bench: Diagnosing Hidden Planning Failures in Long-Horizon Tool-Calling Agents Beyond Success Rate▲3.9k1.75
[PDF]AneumoBench: A Source-Linked Benchmark for Synthetic-Geometry Transfer in Aneurysm CFD▲3.0k2.33
Withdrawn or desk rejected (117)
[PDF]Counterfactual Auditing of Object Presence and Quantity Judgments in Vision-Language ModelsWithdrawn1.67
[PDF]Correlation Does Not Certify a Policy Choice: What Benchmarks Should Publish InsteadWithdrawn2.33
[PDF]EarthArena: Benchmarking Agents on Real-world, Long-Horizon Scientific Tasks in Earth ObservationWithdrawn1.67
[PDF]AskInfer-Bench: Profiles Are Evidence, Not Intent Labels, in Personalized Deep ResearchWithdrawn1.00
[PDF]CommerceAgentBench: Benchmarking Long-Horizon Agents in High-Fidelity, Stateful, and Reproducible Replicas of Real Online ServicesDesk rejected2.00