GPT-OSS-120B (Reasoning): benchmark results

Provider: OpenAI. Released 2025-08-05. Access: Open.

Aggregate Rating 1565 ± 14, rank #885 of 2287 rated models, from 146 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
SEA-HELM (English) - LiveCodeBench v668.18Normalized Score91.7
BALSAM - Question Answering73.39Overall score (0-100, LLM-judged generation and multiple cho88.7
SEA-HELM (English) - MathArena45.45Normalized Score88.3
BALSAM - Overall55.91Mean of category overall scores (0-100)82.8
SEA-HELM (Filipino) - SEA-Safeguard75.89Normalized Score81.1
BALSAM - Entailment79.5Overall score (0-100, LLM-judged generation and multiple cho80.6
BALSAM - Text Classification39.35Overall score (0-100, LLM-judged generation and multiple cho80
SEA-HELM (Tamil) - SEA-MT-Bench (LLM Judge)79.82Normalized Score77
BALSAM - Program Execution93.78Overall score (0-100, LLM-judged generation and multiple cho75.8
BALSAM - Sequence Tagging40.38Overall score (0-100, LLM-judged generation and multiple cho75
SEA-HELM (Thai) - SEA-MT-Bench (LLM Judge)83.26Normalized Score74.3
BALSAM - Reading Comprehension56.77Overall score (0-100, LLM-judged generation and multiple cho74.2

Interactive version: theaggregate.ai/model?slug=gpt-oss-120b-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-22.