Skip to content
← Back to explorer

HFEPX Benchmark Hub

MMLU Or HotpotQA Or LiveCodeBench Benchmark Papers

Updated from current HFEPX corpus (Apr 25, 2026). 54 papers are grouped in this benchmark page.

Read Full Context

Updated from current HFEPX corpus (Apr 25, 2026). 54 papers are grouped in this benchmark page. Common evaluation modes: Automatic Metrics, Simulation Env. Most common rater population: Domain Experts. Common annotation unit: Trajectory. Frequent quality control: Calibration. Frequently cited benchmark: HotpotQA. 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 Mar 28, 2026.

Papers: 54 Last published: Mar 28, 2026 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%

54 / 54 sampled papers are not low-signal flagged.

Replication-Ready Set

13

Papers with explicit benchmark + metric + eval mode fields.

Quality Controls

1.9%

1 papers report calibration/adjudication/IAA controls.

  • 19 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

  • 52.6% of papers report explicit human-feedback signals, led by pairwise preferences.
  • automatic metrics appears in 24.1% of papers in this hub.
  • HotpotQA 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 (1.9% of papers).
  • Rater context is mostly domain experts, and annotation is commonly trajectory-level annotation; use this to scope replication staffing.
  • Pair this hub with a human_eval-heavy hub to validate judge-model calibration.

Benchmark Interpretation

  • HotpotQA appears in 36.8% of hub papers (7/54); use this cohort for benchmark-matched comparisons.
  • MMLU appears in 36.8% of hub papers (7/54); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • accuracy is reported in 57.9% of hub papers (11/54); compare with a secondary metric before ranking methods.
  • cost is reported in 31.6% of hub papers (6/54); 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
PubMed Reasoner: Dynamic Reasoning-based Retrieval for Evidence-Grounded Biomedical Question Answering

Mar 28, 2026

 Llm As Judge, Automatic Metrics Expert Verification Accuracy, Relevance Not reported
Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters

Feb 11, 2026

 Not reported Pairwise Preference Latency, Cost Not reported
$V_1$: Unifying Generation and Self-Verification for Parallel Reasoners

Mar 4, 2026

 Automatic Metrics Pairwise Preference Pass@1 Not reported
Duel-Evolve: Reward-Free Test-Time Scaling via LLM Self-Preferences

Feb 25, 2026

 Automatic Metrics Pairwise Preference Accuracy Not reported
Team of Thoughts: Efficient Test-time Scaling of Agentic Systems through Orchestrated Tool Calling

Feb 18, 2026

 Automatic Metrics Not reported Accuracy Calibration
How Reliable is Language Model Micro-Benchmarking?

Oct 9, 2025

 Automatic Metrics Pairwise Preference Accuracy, Cost 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
Learning When to Sample: Confidence-Aware Self-Consistency for Efficient LLM Chain-of-Thought Reasoning

Mar 9, 2026

 Automatic Metrics Not reported Accuracy, Cost Not reported
D-COT: Disciplined Chain-of-Thought Learning for Efficient Reasoning in Small Language Models

Feb 25, 2026

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

Checklist

  • Strong: Papers with explicit human feedback

    Coverage is strong (52.6% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (5.3% vs 30% target).

  • Strong: Papers naming benchmarks/datasets

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

  • Strong: Papers naming evaluation metrics

    Coverage is strong (73.7% vs 35% target).

  • Gap: Papers with known rater population

    Coverage is a replication risk (15.8% vs 35% target).

  • Strong: Papers with known annotation unit

    Coverage is strong (36.8% vs 35% target).

Strengths

  • Strong human-feedback signal (52.6% of papers).
  • Most papers provide measurable evaluation context (100% benchmarks, 73.7% metrics).
  • Agentic evaluation appears in 52.6% of papers.

Known Gaps

  • Only 5.3% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (15.8% coverage).
  • LLM-as-judge appears without enough inter-annotator agreement reporting.

Suggested Next Analyses

  • Pair this hub with a human_eval-heavy hub to validate judge-model calibration.
  • Stratify by benchmark (HotpotQA vs MMLU) before comparing methods.
  • Track metric sensitivity by reporting both accuracy and cost.
  • Add inter-annotator agreement checks when reproducing these protocols.

Recommended Queries

LLM-as-Judge ProtocolsBenchmark Slice: HotpotQAMetric Slice: accuracyRecent High-Signal Papers
Known Limitations
  • Only 5.3% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (15.8% 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 (13)
  • Simulation Env (2)
  • Llm As Judge (1)

Human Feedback Mix

  • Pairwise Preference (6)
  • Demonstrations (2)
  • Critique Edit (1)
  • Expert Verification (1)

Top Benchmarks

  • HotpotQA (7)
  • MMLU (7)
  • LiveCodeBench (5)
  • MMLU Pro (3)

Top Metrics

  • Accuracy (11)
  • Cost (6)
  • Latency (3)
  • F1 (2)

Top Papers On This Benchmark

Related Benchmark Hubs

MMLU Or HotpotQA Benchmark Papers MMLU Or LiveCodeBench Benchmark Papers MMLU Or AIME Or HotpotQA Benchmark Papers MMLU Or MATH-500 Or HotpotQA Benchmark Papers MMLU Or SWE-bench Or HotpotQA Benchmark Papers MMLU Or MATH-500 Or LiveCodeBench 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