Skip to content
← Back to explorer

\$OneMillion-Bench: How Far are Language Agents from Human Experts?

Qianyu Yang, Yang Liu, Jiaqi Li, Jun Bai, Hao Chen, Kaiyuan Chen, Tiliang Duan, Jiayun Dong, Xiaobo Hu, Zixia Jia, Yang Liu, Tao Peng, Yixin Ren, Ran Tian, Zaiyuan Wang, Yanglihong Xiao, Gang Yao, Lingyue Yin, Ge Zhang, Chun Zhang, Jianpeng Jiao, Zilong Zheng, Yuan Gong · Mar 9, 2026 · Citations: 0

Automatic Metrics Law Long Horizon Rubric Rating Tool Use
Open arXiv Find Implementation RSS feed Shortlist (0)

Data freshness

Extraction: Fresh

Check recency before relying on this page for active eval decisions. Use stale pages as context and verify against current hub results.

Metadata refreshed

Mar 9, 2026, 5:32 AM

Recent

Extraction refreshed

Mar 14, 2026, 5:00 AM

Fresh

Extraction source

Persisted extraction

Confidence 0.80

Abstract

As language models (LMs) evolve from chat assistants to long-horizon agents capable of multi-step reasoning and tool use, existing benchmarks remain largely confined to structured or exam-style tasks that fall short of real-world professional demands. To this end, we introduce \$OneMillion-Bench \$OneMillion-Bench, a benchmark of 400 expert-curated tasks spanning Law, Finance, Industry, Healthcare, and Natural Science, built to evaluate agents across economically consequential scenarios. Unlike prior work, the benchmark requires retrieving authoritative sources, resolving conflicting evidence, applying domain-specific rules, and making constraint decisions, where correctness depends as much on the reasoning process as the final answer. We adopt a rubric-based evaluation protocol scoring factual accuracy, logical coherence, practical feasibility, and professional compliance, focused on expert-level problems to ensure meaningful differentiation across agents. Together, \$OneMillion-Bench provides a unified testbed for assessing agentic reliability, professional depth, and practical readiness in domain-intensive scenarios.

HFEPX Relevance Assessment

This paper has useful evaluation signal, but protocol completeness is partial; pair it with related papers before deciding implementation strategy.

Best use

Secondary protocol comparison source

Use if you need

A benchmark-and-metrics comparison anchor.

Main weakness

No major weakness surfaced.

Trust level

High

Eval-Fit Score

65/100 • Medium

Useful as a secondary reference; validate protocol details against neighboring papers.

Human Feedback Signal

Detected

Evaluation Signal

Detected

HFEPX Fit

Moderate-confidence candidate

Extraction confidence: High

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

Field Provenance & Confidence

Each key protocol field shows extraction state, confidence band, and data source so you can decide whether to trust it directly or validate from full text.

Human Feedback Types

strong

Rubric Rating

Confidence: High Source: Persisted extraction evidenced

Directly usable for protocol triage.

Evidence snippet: As language models (LMs) evolve from chat assistants to long-horizon agents capable of multi-step reasoning and tool use, existing benchmarks remain largely confined to structured or exam-style tasks that fall short of real-world professional demands.

Evaluation Modes

strong

Automatic Metrics

Confidence: High Source: Persisted extraction evidenced

Includes extracted eval setup.

Evidence snippet: As language models (LMs) evolve from chat assistants to long-horizon agents capable of multi-step reasoning and tool use, existing benchmarks remain largely confined to structured or exam-style tasks that fall short of real-world professional demands.

Quality Controls

missing

Not reported

Confidence: Low Source: Persisted extraction missing

No explicit QC controls found.

Evidence snippet: As language models (LMs) evolve from chat assistants to long-horizon agents capable of multi-step reasoning and tool use, existing benchmarks remain largely confined to structured or exam-style tasks that fall short of real-world professional demands.

Benchmarks / Datasets

strong

Onemillion Bench

Confidence: High Source: Persisted extraction evidenced

Useful for quick benchmark comparison.

Evidence snippet: To this end, we introduce \$OneMillion-Bench \$OneMillion-Bench, a benchmark of 400 expert-curated tasks spanning Law, Finance, Industry, Healthcare, and Natural Science, built to evaluate agents across economically consequential scenarios.

Reported Metrics

strong

Accuracy, Coherence

Confidence: High Source: Persisted extraction evidenced

Useful for evaluation criteria comparison.

Evidence snippet: We adopt a rubric-based evaluation protocol scoring factual accuracy, logical coherence, practical feasibility, and professional compliance, focused on expert-level problems to ensure meaningful differentiation across agents.

Rater Population

strong

Domain Experts

Confidence: High Source: Persisted extraction evidenced

Helpful for staffing comparability.

Evidence snippet: To this end, we introduce \$OneMillion-Bench \$OneMillion-Bench, a benchmark of 400 expert-curated tasks spanning Law, Finance, Industry, Healthcare, and Natural Science, built to evaluate agents across economically consequential scenarios.

Human Data Lens

  • Uses human feedback: Yes
  • Feedback types: Rubric Rating
  • Rater population: Domain Experts
  • Unit of annotation: Multi Dim Rubric
  • Expertise required: Law
  • Extraction source: Persisted extraction

Evaluation Lens

  • Evaluation modes: Automatic Metrics
  • Agentic eval: Tool Use, Long Horizon
  • Quality controls: Not reported
  • Confidence: 0.80
  • Flags: None

Protocol And Measurement Signals

Benchmarks / Datasets

Onemillion-Bench

Reported Metrics

accuracycoherence

Research Brief

Deterministic synthesis

As language models (LMs) evolve from chat assistants to long-horizon agents capable of multi-step reasoning and tool use, existing benchmarks remain largely confined to structured or exam-style tasks that fall short of real-world… HFEPX signals include Rubric Rating, Automatic Metrics, Tool Use with confidence 0.80. Updated from current HFEPX corpus.

Generated Mar 14, 2026, 5:00 AM · Grounded in abstract + metadata only

Key Takeaways

  • As language models (LMs) evolve from chat assistants to long-horizon agents capable of multi-step reasoning and tool use, existing benchmarks remain largely confined to structured…
  • To this end, we introduce \OneMillion-Bench \OneMillion-Bench, a benchmark of 400 expert-curated tasks spanning Law, Finance, Industry, Healthcare, and Natural Science, built to…

Researcher Actions

  • Compare its human-feedback setup against pairwise and rubric hubs.
  • Cross-check benchmark overlap: Onemillion-Bench.
  • Validate metric comparability (accuracy, coherence).

Caveats

  • Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
  • Extraction confidence is probabilistic and should be validated for critical decisions.

Research Summary

Contribution Summary

  • As language models (LMs) evolve from chat assistants to long-horizon agents capable of multi-step reasoning and tool use, existing benchmarks remain largely confined to structured or exam-style tasks that fall short of real-world…
  • To this end, we introduce \OneMillion-Bench \OneMillion-Bench, a benchmark of 400 expert-curated tasks spanning Law, Finance, Industry, Healthcare, and Natural Science, built to evaluate agents across economically consequential scenarios.
  • We adopt a rubric-based evaluation protocol scoring factual accuracy, logical coherence, practical feasibility, and professional compliance, focused on expert-level problems to ensure meaningful differentiation across agents.

Why It Matters For Eval

  • To this end, we introduce \OneMillion-Bench \OneMillion-Bench, a benchmark of 400 expert-curated tasks spanning Law, Finance, Industry, Healthcare, and Natural Science, built to evaluate agents across economically consequential scenarios.
  • We adopt a rubric-based evaluation protocol scoring factual accuracy, logical coherence, practical feasibility, and professional compliance, focused on expert-level problems to ensure meaningful differentiation across agents.

Researcher Checklist

  • Pass: Human feedback protocol is explicit

    Detected: Rubric Rating

  • Pass: Evaluation mode is explicit

    Detected: Automatic Metrics

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Pass: Benchmark or dataset anchors are present

    Detected: Onemillion-Bench

  • Pass: Metric reporting is present

    Detected: accuracy, coherence

Related Papers

Papers are ranked by protocol overlap, extraction signal alignment, and semantic proximity.

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

Post a Job Get a Quote