readable AI benchmarks (simplified)
OpenAI
GPT-5.6 Luna (Non-reasoning)
GPT-5.6 Luna (Non-reasoning) has a Quality Score of 30.7, ranking 262nd among 571 scored models. Per 1M tokens, pricing is $0.200 input, $1.20 output, $0.020 cached input, and $0.250 cache write. It has a 1M token context window. Its Reliability Score is 37.5, ranking 258th among 573 scored models, above average (total average: 36.5). Its Value Score is 26.2, low compared with the total Value average of 31.4.
Quality Score30.7coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score26.2
Factual reliability37.5
Cache Discount90%
Model specification
- Reasoning
- non-reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 1M tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $0.200
- Output
- $1.20
- Cached Input
- $0.020
- Cache write
- $0.250
- Cost per task
- $0.010
Capability
- Intelligence
- 15.5
- Coding
- not available
- Agentic
- not available
- Omniscience
- -24.9
- Correct
- 28.6%
- Blended price
- $0.174
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 82.1%
Correct 28.6%Incorrect 53.5%Partial / not attempted 17.8%
Artificial Analysis benchmarks
- GDPval-AA v2
- 21%
- τ³-Banking
- 10%
- SciCode
- 40%
- Humanity’s Last Exam
- 7%
- GPQA Diamond
- 65%
- CritPt
- 0%
- AA-Omniscience
- 38%
- AA-LCR
- 43%
Similar models
- GPT-6 Luna (Non-reasoning)OpenAIQuality Score 33.7Value Score 30.8
- GPT-5.2 (Non-reasoning)OpenAIQuality Score 35.0Value Score 22.7
- GPT-5.1 (Non-reasoning)OpenAIQuality Score 26.6Value Score 18.0
- GPT-5.4 (Non-reasoning)OpenAIQuality Score 35.1Value Score 22.3
- GPT-4o (Nov '24)OpenAIQuality Score 28.9Value Score 18.1
- GPT-4.1OpenAIQuality Score 24.9Value Score 16.5