Skip to content
← Back to explorer

HFEPX Benchmark Hub

DROP Or AIME Or MATH-500 Benchmark Papers

Updated from current HFEPX corpus (Apr 17, 2026). 59 papers are grouped in this benchmark page.

Read Full Context

Updated from current HFEPX corpus (Apr 17, 2026). 59 papers are grouped in this benchmark page. Common evaluation modes: Automatic Metrics, Llm As Judge. Most common rater population: Domain Experts. Common annotation unit: Trajectory. Frequent quality control: Gold Questions. Frequently cited benchmark: DROP. Common metric signal: accuracy. Use this page to compare protocol setup, judge behavior, and labeling design decisions before running new eval experiments. Newest paper in this set is from Dec 26, 2025.

Papers: 59 Last published: Dec 26, 2025 Global RSS

Researcher Quick Triage

Use this page for benchmark-matched method comparisons and eval protocol selection. Quality band: High .

High-Signal Coverage

100.0%

59 / 59 sampled papers are not low-signal flagged.

Replication-Ready Set

14

Papers with explicit benchmark + metric + eval mode fields.

Quality Controls

1.7%

1 papers report calibration/adjudication/IAA controls.

  • 17 papers explicitly name benchmark datasets in the sampled set.
  • 14 papers report at least one metric term in metadata extraction.
  • Start with the ranked shortlist below before reading all papers.

Primary action: Start with the top 2 benchmark-matched papers, then compare evaluation modes in the protocol matrix.

Why This Matters (Expanded)

Why This Matters For Eval Research

  • 16.9% of papers report explicit human-feedback signals, led by pairwise preferences.
  • automatic metrics appears in 23.7% of papers in this hub.
  • DROP is a recurring benchmark anchor for cross-paper comparisons in this page.
Protocol Notes (Expanded)

Protocol Takeaways

  • Most common quality-control signal is gold-question checks (1.7% of papers).
  • Rater context is mostly domain experts, and annotation is commonly trajectory-level annotation; use this to scope replication staffing.
  • Compare papers that report both human_eval and llm_as_judge to quantify judge-human agreement drift.

Benchmark Interpretation

  • DROP appears in 61% of hub papers (36/59); use this cohort for benchmark-matched comparisons.
  • AIME appears in 28.8% of hub papers (17/59); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • accuracy is reported in 33.9% of hub papers (20/59); compare with a secondary metric before ranking methods.
  • cost is reported in 22% of hub papers (13/59); compare with a secondary metric before ranking methods.

Start Here (Benchmark-Matched First 6)

Ranked by protocol completeness so you can quickly find papers suitable for comparison studies.

Protocol Matrix (Top 10)

Compare protocol ingredients quickly before deep-reading full papers.

Paper Eval Modes Human Feedback Metrics Quality Controls
CricBench: A Multilingual Benchmark for Evaluating LLMs in Cricket Analytics

Dec 26, 2025

 Automatic Metrics Expert Verification Accuracy Gold Questions
FairMed-XGB: A Bayesian-Optimised Multi-Metric Framework with Explainability for Demographic Equity in Critical Healthcare Data

Mar 16, 2026

 Automatic Metrics Expert Verification Accuracy, Auroc Not reported
$V_1$: Unifying Generation and Self-Verification for Parallel Reasoners

Mar 4, 2026

 Automatic Metrics Pairwise Preference Pass@1 Not reported
GIFT: Group-Relative Implicit Fine-Tuning Integrates GRPO with DPO and UNA

Oct 27, 2025

 Automatic Metrics Pairwise Preference Mse Not reported
Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation

Oct 5, 2025

 Automatic Metrics, Simulation Env Rubric Rating Accuracy, Pass@k Not reported
Dyslexify: A Mechanistic Defense Against Typographic Attacks in CLIP

Aug 28, 2025

 Automatic Metrics Red Team Accuracy Not reported
Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Jun 3, 2025

 Automatic Metrics Critique Edit Pass@1 Not reported
LLM-as-a-Judge for Time Series Explanations

Apr 2, 2026

 Llm As Judge, Automatic Metrics Not reported Accuracy, Faithfulness Not reported
S0 Tuning: Zero-Overhead Adaptation of Hybrid Recurrent-Attention Models

Apr 1, 2026

 Automatic Metrics Not reported Pass@1, Cost Not reported
SpatiaLab: Can Vision-Language Models Perform Spatial Reasoning in the Wild?

Feb 3, 2026

 Automatic Metrics Not reported Accuracy Not reported
Researcher Workflow (Detailed)

Checklist

  • Gap: Papers with explicit human feedback

    Coverage is a replication risk (16.9% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (1.7% vs 30% target).

  • Strong: Papers naming benchmarks/datasets

    Coverage is strong (100% vs 35% target).

  • Strong: Papers naming evaluation metrics

    Coverage is strong (66.1% vs 35% target).

  • Gap: Papers with known rater population

    Coverage is a replication risk (3.4% vs 35% target).

  • Gap: Papers with known annotation unit

    Coverage is a replication risk (10.2% vs 35% target).

Strengths

  • Most papers provide measurable evaluation context (100% benchmarks, 66.1% metrics).
  • Contains both human-eval and LLM-as-judge protocols for head-to-head methodology comparison.

Known Gaps

  • Only 1.7% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (3.4% coverage).
  • Annotation unit is under-specified (10.2% coverage).

Suggested Next Analyses

  • Compare papers that report both human_eval and llm_as_judge to quantify judge-human agreement drift.
  • Stratify by benchmark (DROP vs AIME) before comparing methods.
  • Track metric sensitivity by reporting both accuracy and cost.
  • Add inter-annotator agreement checks when reproducing these protocols.

Recommended Queries

Judge vs Human AgreementBenchmark Slice: DROPMetric Slice: accuracyRecent High-Signal Papers
Known Limitations
  • Only 1.7% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (3.4% coverage).
  • Narrative synthesis is grounded in metadata and abstracts only; full-paper implementation details are not parsed.
Research Utility Snapshot (Detailed)

Evaluation Modes

  • Automatic Metrics (14)
  • Llm As Judge (2)
  • Simulation Env (2)
  • Human Eval (1)

Human Feedback Mix

  • Pairwise Preference (4)
  • Expert Verification (2)
  • Critique Edit (1)
  • Demonstrations (1)

Top Benchmarks

  • DROP (36)
  • AIME (17)
  • MATH 500 (12)
  • GSM8K (7)

Top Metrics

  • Accuracy (20)
  • Cost (13)
  • Pass@1 (5)
  • Latency (3)

Top Papers On This Benchmark

Related Benchmark Hubs

DROP Or AIME Benchmark Papers DROP Or GSM8K Or AIME Benchmark Papers DROP Or AIME Or GPQA Benchmark Papers DROP Or AIME Or AlpacaEval Benchmark Papers DROP Or AIME Or WebArena Benchmark Papers DROP Or AIME Or SWE-bench Benchmark Papers MATH-500 Or GPQA Benchmark Papers (20) MMLU Or AIME Or AlpacaEval Benchmark Papers (48) MMLU Or AIME Or GPQA Benchmark Papers (42) GSM8K Or MMLU Or AIME Benchmark Papers (57) MMLU Or AIME Or MATH-500 Benchmark Papers (46) MMLU Or AIME Or SWE-bench Benchmark Papers (51) MMLU Or AIME Benchmark Papers (39) MMLU Or AlpacaEval Or GPQA Benchmark Papers (39) GSM8K Or MMLU Or AlpacaEval Benchmark Papers (51) MMLU Or MATH-500 Or AlpacaEval Benchmark Papers (44) MMLU Or SWE-bench Or AlpacaEval Benchmark Papers (45) MMLU Or AlpacaEval Benchmark Papers (32) GSM8K Or MMLU Or GPQA Benchmark Papers (48) MMLU Or MATH-500 Or GPQA Benchmark Papers (39) MMLU Or SWE-bench Or GPQA Benchmark Papers (42) MMLU Or GPQA Benchmark Papers (29) GSM8K Or MMLU Or MATH-500 Benchmark Papers (50) GSM8K Or MMLU Or SWE-bench Benchmark Papers (55)
Get Started

Join the #1 Platform for AI Training Talent

Where top AI builders and expert AI Trainers connect to build the future of AI.
Self-Service
Post a Job
Post your project and get a shortlist of qualified AI Trainers and Data Labelers. Hire and manage your team in the tools you already use.
Create Account & Post a Job
Managed Service
For Large Projects
Done-for-You
We recruit, onboard, and manage a dedicated team inside your tools. End-to-end operations for large or complex projects.
Learn About Managed Service
For Freelancers
Join as an AI Trainer
Find AI training and data labeling projects across platforms, all in one place. One profile, one application process, more opportunities.
Join Now