GPT OSS 120B
- Made by
- OpenAI
- Released
- 5 August 2025
- Licence
- open
- Size
- 117B
- Context
- 131K
How this score is made
- HealthBench ProfessionalNo result here, and none is filled in.
- HealthBench57.657.6 out of 100runs −0.5 leveladjusted 58.1weight 0.798, coremodel cardReported by the maker.reasoning level high, raw score (%), gpt-oss model card Table 3 (low 53.0, medium 55.9)
- Health Optimization Bench: incretinNo result here, and none is filled in.
- SAFE-TeenNo result here, and none is filled in.
- Adjusted result, one benchmark
- 58.1
- Field average, counts for 60% with 1 of 4 benchmarks
- 55.3
- Index
- = 56.4
Benchmark by benchmark
HealthBench17 of 26
- 68.1Claude Opus 5.5
- 67.1Claude Opus 5
- 65.4Claude Sonnet 5.5
- 65.1Baichuan-M3
- 63.3GPT-5.2-High
- 62.7Claude Fable 5
- 61.6Claude Haiku 5.5
- 60Claude Fable 5.1
- 59.3Claude Opus 4.8
- 57.6GPT OSS 120B
26 modelsFull benchmark
Artificial Analysis Healthcare & Medical Index28 of 29
- 61Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)
- 58Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)
- 53Claude Opus 5 (Adaptive Reasoning, Max Effort)
- 52Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)
- 52GPT-6 Astra (max)
- 50Muse Spark 1.3 (max)
- 47GLM-5.3 (max)
- 47Grok 4.7 (xhigh)
- 45GLM 5.3 Flash
- 14gpt-oss-120b (high)
29 modelsFull benchmark