readable AI benchmarks (simplified)
OpenAI
gpt-oss-20b (Low)
gpt-oss-20b (Low) has a Quality Score of 18.0, ranking 447th among 571 scored models. Per 1M tokens, pricing is $0.070 input and $0.215 output. It has a 131,072 token context window. Its Reliability Score is 20.7, ranking 466th among 573 scored models, below average (total average: 36.5).
Quality Score18.0coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability20.7
Cache Discountnot available
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 131,072 tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.070
- Output
- $0.215
- Cached Input
- not available
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 10.0
- Coding
- not available
- Agentic
- not available
- Omniscience
- -58.5
- Correct
- 15.1%
- Blended price
- not available
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 88.7%
Correct 15.1%Incorrect 73.6%Partial / not attempted 11.3%
Artificial Analysis benchmarks
- Humanity’s Last Exam
- 5%
- GPQA Diamond
- 61%
- CritPt
- 0%
- AA-Omniscience
- 21%
- AA-LCR
- 31%
Similar models
- gpt-oss-120b (Low)OpenAIQuality Score 19.5Value Score 16.5
- gpt-oss-20b (High)OpenAIQuality Score 16.1Value Score not available
- gpt-oss-120b (High)OpenAIQuality Score 21.6Value Score 18.4
- o3-mini (High)OpenAIQuality Score 22.8Value Score 15.9
- GPT-5 nano (High)OpenAIQuality Score 27.8Value Score 26.0
- GPT-5 nano (Medium)OpenAIQuality Score 28.2Value Score 26.3