readable AI benchmarks (simplified)
OpenAI
GPT-5.6 Sol (Non-reasoning)
GPT-5.6 Sol (Non-reasoning) has a Quality Score of 47.1, ranking 137th among 577 scored models. Per 1M tokens, pricing is $4.00 input, $20.00 output, $0.400 cached input, and $5.00 cache write. It has a 1M token context window. Its Reliability Score is 50.5, ranking 123rd among 579 scored models, above average (total average: 36.6). Its Value Score is 28.8, around average compared with the total Value average of 31.8.
Quality Score47.1coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score28.8
Factual reliability50.5
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
- $4.00
- Output
- $20.00
- Cached Input
- $0.400
- Cache write
- $5.00
- Cost per task
- not available
Capability
- Intelligence
- 28.3
- Coding
- not available
- Agentic
- not available
- Omniscience
- 1.1
- Correct
- 48.7%
- Blended price
- $3.08
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 96.3%
Correct 48.7%Incorrect 47.6%Partial / not attempted 3.7%
Artificial Analysis benchmarks
- GDPval-AA v2
- 37%
- τ³-Banking
- 20%
- SciCode
- 48%
- Humanity’s Last Exam
- 17%
- GPQA Diamond
- 79%
- CritPt
- 5%
- AA-Omniscience
- 51%
- AA-LCR
- 62%
Similar models
- GPT-6 Sol (Non-reasoning)OpenAIQuality Score 46.7Value Score 31.0
- GPT-5.5 (Non-reasoning)OpenAIQuality Score 41.6Value Score 24.5
- GPT-5.6 Terra (Non-reasoning)OpenAIQuality Score 35.2Value Score 23.0
- GPT-5.4 (Non-reasoning)OpenAIQuality Score 35.1Value Score 22.3
- GPT-5.2 (Non-reasoning)OpenAIQuality Score 35.0Value Score 22.7
- GPT-6 Luna (Non-reasoning)OpenAIQuality Score 33.7Value Score 30.8