readable AI benchmarks (simplified)
OpenAI
gpt-oss-120b (High)
gpt-oss-120b (High) has a Quality Score of 21.6, ranking 371st among 571 scored models. Per 1M tokens, pricing is $0.150 input, $0.595 output, and $0.125 cached input. It accepts text input, outputs text, and has a 131,072 token context window. Its Reliability Score is 25.4, ranking 392nd among 573 scored models, below average (total average: 36.5). Its Value Score is 18.4, low compared with the total Value average of 31.4.
Quality Score21.6coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score18.4
Factual reliability25.4
Cache Discount17%
Model specification
- Reasoning
- reasoning
- Input modalities
- text
- Output modalities
- text
- Context window
- 131,072 tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.150
- Output
- $0.595
- Cached Input
- $0.125
- Cache write
- not available
- Cost per task
- $0.107
Capability
- Intelligence
- 11.6
- Coding
- not available
- Agentic
- not available
- Omniscience
- -49.3
- Correct
- 21.8%
- Blended price
- $0.177
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 92.8%
Correct 21.8%Incorrect 71.0%Partial / not attempted 7.2%
Artificial Analysis benchmarks
- GDPval-AA v2
- 6%
- τ³-Banking
- 13%
- SciCode
- 34%
- Humanity’s Last Exam
- 20%
- GPQA Diamond
- 78%
- CritPt
- 1%
- AA-Omniscience
- 25%
- AA-LCR
- 52%
Similar models
- o3-mini (High)OpenAIQuality Score 22.8Value Score 15.9
- gpt-oss-120b (Low)OpenAIQuality Score 19.5Value Score 16.5
- gpt-oss-20b (Low)OpenAIQuality Score 18.0Value Score not available
- GPT-5 nano (High)OpenAIQuality Score 27.8Value Score 26.0
- gpt-oss-20b (High)OpenAIQuality Score 16.1Value Score not available
- GPT-5 nano (Medium)OpenAIQuality Score 28.2Value Score 26.3