Vibeleaderboard
← Benchmark guide

Model results

ReactBench

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

ReactBench

Source
ReactBench (reviewed publisher results)
Version
1.1
Measurement date
Not reported
Metric
% · Higher is better
Evaluation scope
Overall pass@1 across tasks; effort=Max; result date not supplied; source captured 2026-09-10

Exact score ties share a position. Positions do not establish statistical significance. Missing metadata is shown as unreported; matching imported metadata is not independent verification of the protocol.

  1. #1GPT-5.6 Sol

    openai/gpt-5.6-sol-20260709

    46.7%

    View modelEvidence independent

  2. #2Claude Fable 5.1

    anthropic/claude-fable-5-1

    45.6%

    View modelEvidence independent

  3. #3Claude Fable 5

    anthropic/claude-fable-5

    43.6%

    View modelEvidence independent

  4. #4Claude Opus 5

    anthropic/claude-opus-5

    42.1%

    View modelEvidence independent

  5. #5GPT-5.6 Terra

    openai/gpt-5.6-terra-20260709

    40.5%

    View modelEvidence independent

  6. #6GPT-5.6 Luna

    openai/gpt-5.6-luna-20260709

    33.8%

    View modelEvidence independent

  7. #7GLM 5.3 Flash

    z-ai/glm-5.3-flash-20260826

    31.3%

    View modelEvidence independent

  8. #8Claude Opus 4.8

    anthropic/claude-opus-4-8

    30.8%

    View modelEvidence independent

  9. #9Claude Sonnet 5

    anthropic/claude-sonnet-5

    29.2%

    View modelEvidence independent

  10. #10GLM 5.3

    z-ai/glm-5.3-20260816

    27.7%

    View modelEvidence independent

  11. #11GLM 5.2

    z-ai/glm-5.2-20260616

    24.1%

    View modelEvidence independent
ReactBench model results | VibeLeaderboard