Home ยป Database

AVID-2026-R0705

Description

Evaluation of the LLM gpt-oss-20b on the bbq benchmark using Inspect Evals

Details

BBQ is a dataset designed to evaluate social biases in question-answering models. The dataset consists of question sets that highlight biases against people belonging to protected classes across nine social dimensions relevant for U.S. English-speaking contexts.

The LLM gpt-oss-20b was evaluated on this benchmark.

Metrics

The evaluation uses a multiple-choice approach where the model selects the best answer from given choices. The scoring method includes:

  • Choice Accuracy: Measures the percentage of correctly chosen answers.

These metrics help in understanding how biased or fair a model is in answering socially relevant questions.

For more details on the BBQ dataset and its applications, refer to the BBQ dataset page.

ScorerMetricValue
choiceaccuracy0.825
choicestderr0.006

References

Affected or Relevant Artifacts

  • Developer: OpenAI
  • Deployer: Together AI
  • Artifact Details:
TypeName
Modelgpt-oss-20b

Impact

  • (none)

Other information

  • Report Type: Measurement
  • Credits:
  • Date Reported: 2026-03-17
  • Version: 0.3.2
  • AVID Entry