AI Research

    GPT-OSS-120B: gPQA Diamond now lists OpenAI’s published launch result of 80.1%; different evaluation settings are not interchangeable

    GPQA Diamond listing reflects OpenAI’s published 80.1% launch result

    GPQA Diamond now lists OpenAI’s published launch result of 80.1%; different evaluation settings are not interchangeable — verified by the OnAirToday AI Progress Tracker against OpenAI's published documentation.

    O

    OnAirToday

    Newsroom

    OnAirToday

    The OnAirToday AI Progress Tracker recorded a verified change to OpenAI's GPT-OSS-120B (version gpt-oss-120b): GPQA Diamond now lists OpenAI’s published launch result of 80.1%; different evaluation settings are not interchangeable.

    GPT-OSS-120B is OpenAI’s open-weight, text-based reasoning model, released under the Apache 2.0 license for local deployment and customization. It supports configurable reasoning effort and tool use, with documented deployment on a single 80 GB GPU using its released quantized weights.

    What changed in this review:

    • Added OpenAI’s published SWE-bench Verified launch result of 62.4%.
    • Removed unconfirmed OTIS Mock AIME, Terminal-Bench, LMArena Text and Aider Polyglot figures.
    • Pricing is provider-dependent; no single OpenAI per-token rate applies to the downloadable model.
    • Capability score 54 → 62
    • Flaws and limitations updated
    • Risks and threats updated

    Teams building on GPT-OSS-120B should confirm limits, pricing and benchmark coverage against the vendor's own documentation before relying on these figures.

    The full profile — capabilities, benchmark citations, known flaws and risk guidance — is on the tracker at /ai-models/gpt-oss-120b.

    References:

    • https://openai.com/index/introducing-gpt-oss/
    • https://huggingface.co/openai/gpt-oss-120b
    • https://github.com/openai/gpt-oss
    • https://github.com/openai/harmony
    AI Analysis

    Generated insight by OnAirToday AI

    Benchmark scores are meaningful only when their evaluation settings are clear. Distinguishing settings helps prevent results from being compared as though they were directly interchangeable.

    Powered by AI • Not a substitute for human analysisMore Insights →
    View the primary source →
    Share
    Filed under:AI Research

    Comments

    Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.

    0/1000