Skip to content
← Back to explorer

HFEPX Benchmark Hub

DROP Or SWE-bench Benchmark Papers

Updated from current HFEPX corpus (Mar 31, 2026). 36 papers are grouped in this benchmark page.

Read Full Context

Updated from current HFEPX corpus (Mar 31, 2026). 36 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: 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: 36 Last published: Dec 26, 2025 Global RSS

Researcher Quick Triage

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

High-Signal Coverage

100.0%

36 / 36 sampled papers are not low-signal flagged.

Replication-Ready Set

7

Papers with explicit benchmark + metric + eval mode fields.

Quality Controls

2.8%

1 papers report calibration/adjudication/IAA controls.

  • 11 papers explicitly name benchmark datasets in the sampled set.
  • 7 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

  • 19.4% of papers report explicit human-feedback signals, led by expert verification.
  • automatic metrics appears in 22.2% 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 (2.8% of papers).
  • Rater context is mostly domain experts, and annotation is commonly trajectory-level annotation; use this to scope replication staffing.
  • Stratify by benchmark (DROP vs SWE-bench) before comparing methods.

Benchmark Interpretation

  • DROP appears in 72.2% of hub papers (26/36); use this cohort for benchmark-matched comparisons.
  • SWE-bench appears in 27.8% of hub papers (10/36); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • accuracy is reported in 25% of hub papers (9/36); compare with a secondary metric before ranking methods.
  • cost is reported in 22.2% of hub papers (8/36); 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
Dyslexify: A Mechanistic Defense Against Typographic Attacks in CLIP

Aug 28, 2025

 Automatic Metrics Red Team Accuracy Not reported
SWE-Protégé: Learning to Selectively Collaborate With an Expert Unlocks Small Language Models as Software Engineering Agents

Feb 25, 2026

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

Feb 3, 2026

 Automatic Metrics Not reported Accuracy Not reported
KLong: Training LLM Agent for Extremely Long-horizon Tasks

Feb 19, 2026

 Not reported Rubric Rating Not reported Not reported
ReCoN-Ipsundrum: An Inspectable Recurrent Persistence Loop Agent with Affect-Coupled Control and Mechanism-Linked Consciousness Indicator Assays

Feb 26, 2026

 Not reported Pairwise Preference Not reported Not reported
AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents

Jun 17, 2025

 Automatic Metrics Not reported Cost Not reported
Structured Agent Distillation for Large Language Model

May 20, 2025

 Simulation Env Demonstrations Not reported Not reported
Researcher Workflow (Detailed)

Checklist

  • Gap: Papers with explicit human feedback

    Coverage is a replication risk (19.4% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (2.8% vs 30% target).

  • Strong: Papers naming benchmarks/datasets

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

  • Strong: Papers naming evaluation metrics

    Coverage is strong (58.3% vs 35% target).

  • Gap: Papers with known rater population

    Coverage is a replication risk (8.3% vs 35% target).

  • Gap: Papers with known annotation unit

    Coverage is a replication risk (11.1% vs 35% target).

Strengths

  • Most papers provide measurable evaluation context (100% benchmarks, 58.3% metrics).

Known Gaps

  • Only 2.8% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (8.3% coverage).
  • Annotation unit is under-specified (11.1% coverage).

Suggested Next Analyses

  • Stratify by benchmark (DROP vs SWE-bench) before comparing methods.
  • Track metric sensitivity by reporting both accuracy and cost.
  • Add inter-annotator agreement checks when reproducing these protocols.

Recommended Queries

Benchmark Slice: DROPMetric Slice: accuracyRecent High-Signal Papers
Known Limitations
  • Only 2.8% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (8.3% 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 (8)
  • Simulation Env (1)

Human Feedback Mix

  • Expert Verification (2)
  • Pairwise Preference (2)
  • Demonstrations (1)
  • Red Team (1)

Top Benchmarks

  • DROP (26)
  • SWE Bench (10)
  • SWE Bench Verified (4)
  • AIME (1)

Top Metrics

  • Accuracy (9)
  • Cost (8)
  • Pass@1 (4)
  • Latency (3)

Top Papers On This Benchmark

Related Benchmark Hubs

DROP Or AIME Or SWE-bench Benchmark Papers DROP Or LMSYS Chatbot Arena Or SWE-bench Benchmark Papers DROP Or MMLU Or SWE-bench Benchmark Papers DROP Or GSM8K Or SWE-bench Benchmark Papers DROP Benchmark Papers DROP Benchmark Papers (Last 365 Days) GSM8K Or MMLU Or AIME Benchmark Papers (36) MMLU Or AIME Or SWE-bench Benchmark Papers (35) MMLU Or AIME Benchmark Papers (26) GSM8K Or MMLU Or SWE-bench Benchmark Papers (35) GSM8K Or MMLU Benchmark Papers (25) MMLU Or SWE-bench Benchmark Papers (24) MMLU In CS.CL Papers (12) MMLU Benchmark Papers (Last 120 Days) (11) MMLU Benchmark Papers (Last 150 Days) (12) MMLU Benchmark Papers (Last 180 Days) (13) MMLU Benchmark Papers (Last 240 Days) (14) MMLU Benchmark Papers (Last 300 Days) (14) MMLU Benchmark Papers (Last 365 Days) (14) MMLU Benchmark Papers (Last 45 Days) (11) MMLU Benchmark Papers (Last 60 Days) (11) MMLU Benchmark Papers (Last 75 Days) (11) MMLU Benchmark Papers (Last 90 Days) (11) MMLU Benchmark Papers (14)

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote