Vibeleaderboard
← Benchmark guide

Model results

DeepResearchBench

Choose a shared evaluation protocol to compare model scores. Versions, sources and configurations stay separate.

Atlas snapshot captured 10/19/2026, 10:20:28 AM UTC. This is an import timestamp, not the evaluation date. Coverage may be incomplete.

Official source
← All evaluation groups

DeepResearchBench

Source
DeepResearch Bench via Epoch AI
Version
Not reported
Measurement date
Not reported
Metric
% · Higher is better
Evaluation scope
effort high · result date not supplied

Positions are withheld because at least one result lacks explicit independent provenance or a documented evaluation scope. Missing metadata is shown as unreported; matching imported metadata is not independent verification of the protocol.

  1. Claude Opus 4.6

    anthropic/claude-opus-4-6

    55.3%

    View modelEvidence aggregated

  2. Claude Sonnet 4.6

    anthropic/claude-sonnet-4-6

    54.9%

    View modelEvidence aggregated

  3. Claude Opus 4.5

    anthropic/claude-opus-4-5

    54.8%

    View modelEvidence aggregated

  4. GPT-5.5

    openai/gpt-5.5-20260423

    54%

    View modelEvidence aggregated

  5. Claude Opus 4.8

    anthropic/claude-opus-4-8

    50.2%

    View modelEvidence aggregated

  6. GPT-5

    openai/gpt-5-2025-08-07

    48.1%

    View modelEvidence aggregated

  7. Gemini 3 Flash Preview

    google/gemini-3-flash-preview-20251217

    47.9%

    View modelEvidence aggregated

  8. Gemini 3.1 Pro Preview

    google/gemini-3.1-pro-preview-20260219

    47.8%

    View modelEvidence aggregated
DeepResearchBench model results | VibeLeaderboard