Skip to content
← Back to explorer

HFEPX Benchmark Hub

GSM8K Or AIME Or HotpotQA Benchmark Papers

Updated from current HFEPX corpus (Apr 25, 2026). 61 papers are grouped in this benchmark page.

Read Full Context

Updated from current HFEPX corpus (Apr 25, 2026). 61 papers are grouped in this benchmark page. Common evaluation modes: Automatic Metrics, Simulation Env. Common annotation unit: Trajectory. Frequent quality control: Calibration. Frequently cited benchmark: GSM8K. 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 Oct 5, 2025.

Papers: 61 Last published: Oct 5, 2025 Global RSS

Researcher Quick Triage

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

Analysis blocks are computed from the loaded sample (60 of 61 papers).

High-Signal Coverage

100.0%

60 / 60 sampled papers are not low-signal flagged.

Replication-Ready Set

20

Papers with explicit benchmark + metric + eval mode fields.

Quality Controls

1.7%

1 papers report calibration/adjudication/IAA controls.

  • 24 papers explicitly name benchmark datasets in the sampled set.
  • 20 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

  • 41.7% of papers report explicit human-feedback signals, led by pairwise preferences.
  • automatic metrics appears in 32.8% of papers in this hub.
  • GSM8K is a recurring benchmark anchor for cross-paper comparisons in this page.
Protocol Notes (Expanded)

Protocol Takeaways

  • Most common quality-control signal is rater calibration (1.6% of papers).
  • Rater context is mostly unspecified rater pools, 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

  • GSM8K appears in 54.2% of hub papers (13/61); use this cohort for benchmark-matched comparisons.
  • HotpotQA appears in 29.2% of hub papers (7/61); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • accuracy is reported in 54.2% of hub papers (13/61); compare with a secondary metric before ranking methods.
  • cost is reported in 25% of hub papers (6/61); 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
$V_1$: Unifying Generation and Self-Verification for Parallel Reasoners

Mar 4, 2026

 Automatic Metrics Pairwise Preference Pass@1 Not reported
Entropy trajectory shape predicts LLM reasoning reliability: A diagnostic study of uncertainty dynamics in chain-of-thought

Mar 19, 2026

 Automatic Metrics Not reported Accuracy, Calibration error Calibration
Stabilizing Iterative Self-Training with Verified Reasoning via Symbolic Recursive Self-Alignment

Mar 23, 2026

 Automatic Metrics Pairwise Preference Accuracy 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
FOR-Prompting: From Objection to Revision via an Asymmetric Prompting Protocol

Oct 2, 2025

 Automatic Metrics Pairwise Preference, Critique Edit 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
Don't Overthink It: Inter-Rollout Action Agreement as a Free Adaptive-Compute Signal for LLM Agents

Apr 9, 2026

 Automatic Metrics Not reported Accuracy Not reported
MemMachine: A Ground-Truth-Preserving Memory System for Personalized AI Agents

Apr 6, 2026

 Automatic Metrics Not reported Accuracy, Recall Not reported
OSCAR: Orchestrated Self-verification and Cross-path Refinement

Apr 2, 2026

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

Checklist

  • Moderate: Papers with explicit human feedback

    Coverage is usable but incomplete (41.7% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (4.2% vs 30% target).

  • Strong: Papers naming benchmarks/datasets

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

  • Strong: Papers naming evaluation metrics

    Coverage is strong (83.3% vs 35% target).

  • Gap: Papers with known rater population

    Coverage is a replication risk (0% vs 35% target).

  • Strong: Papers with known annotation unit

    Coverage is strong (50% vs 35% target).

Strengths

  • Most papers provide measurable evaluation context (100% benchmarks, 83.3% metrics).
  • Contains both human-eval and LLM-as-judge protocols for head-to-head methodology comparison.
  • Agentic evaluation appears in 58.3% of papers.

Known Gaps

  • Only 4.2% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (0% coverage).
  • LLM-as-judge appears without enough inter-annotator agreement reporting.

Suggested Next Analyses

  • Compare papers that report both human_eval and llm_as_judge to quantify judge-human agreement drift.
  • Stratify by benchmark (GSM8K vs HotpotQA) 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: GSM8KMetric Slice: accuracyRecent High-Signal Papers
Known Limitations
  • Only 4.2% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (0% 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 (20)
  • Simulation Env (3)
  • Human Eval (1)
  • Llm As Judge (1)

Human Feedback Mix

  • Pairwise Preference (5)
  • Critique Edit (3)
  • Demonstrations (2)
  • Rubric Rating (1)

Top Benchmarks

  • GSM8K (13)
  • HotpotQA (7)
  • AIME (6)
  • MATH 500 (4)

Top Metrics

  • Accuracy (13)
  • Cost (6)
  • Pass@1 (3)
  • F1 (2)

Top Papers On This Benchmark

Related Benchmark Hubs

GSM8K Or AIME Benchmark Papers GSM8K Or MATH-500 Or HotpotQA Benchmark Papers GSM8K Or AIME Or MATH-500 Benchmark Papers GSM8K Or AIME Or HumanEval+ Benchmark Papers GSM8K Or AIME Or GPQA Benchmark Papers GSM8K Or GPQA Or HotpotQA Benchmark Papers DROP Benchmark Papers (Last 30 Days) (19) GPQA Or HumanEval+ Benchmark Papers (21) MATH-500 Or GPQA Benchmark Papers (25) MATH-500 Or HumanEval+ Benchmark Papers (23) MATH-500 Benchmark Papers (15) MMLU Or AIME Or AlpacaEval Benchmark Papers (59) MMLU Or AIME Or GPQA Benchmark Papers (53) GSM8K Or MMLU Or AIME Benchmark Papers (71) MMLU Or AIME Or HotpotQA Benchmark Papers (61) MMLU Or AIME Or HumanEval+ Benchmark Papers (56) MMLU Or AIME Or LiveCodeBench Benchmark Papers (58) MMLU Or AIME Or LongBench Benchmark Papers (58) MMLU Or AIME Or MATH-500 Benchmark Papers (57) MMLU Or AIME Or SWE-bench Benchmark Papers (63) MMLU Or AIME Benchmark Papers (49) GSM8K Or MMLU Or AlpacaEval Benchmark Papers (64) MMLU Or MATH-500 Or AlpacaEval Benchmark Papers (55) MMLU Or SWE-bench Or AlpacaEval Benchmark Papers (56)
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