readable AI benchmarks (simplified)
OpenAI
GPT-6 Sol (high)
GPT-6 Sol (high) has a Quality Score of 60.9, ranking 31st among 282 scored models. Per 1M tokens, pricing is $2.00 input, $10.00 output, $0.200 cached input, and $2.50 cache write. It has a 872k token context window. Its Reliability Score is 63.4, ranking 31st among 282 scored models, above average (total average: 36.9). Its Value Score is 39.2, high compared with the total Value average of 30.3.
Quality Score60.9coverage 78.8%: missing Epoch General ECI, Coding, CursorBench 3.2, Agentic and DeepSWE v1.1
Value Score39.2
Reliability63.4
Cache Discount90%
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 872k tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $2.00
- Output
- $10.00
- Cached Input
- $0.200
- Cache write
- $2.50
- Cost per task
- $0.375
Capability
- Intelligence
- 42.8
- Coding
- not available
- Agentic
- not available
- Omniscience
- 26.8
- Correct
- 53.7%
- Blended price
- $1.54
Answer outcomes
Attempt rate: 80.6%
Correct 53.7%Incorrect 26.9%Abstained 19.4%
Artificial Analysis benchmarks
- GDPval-AA v2
- 44%
- SciCode
- 55%
- Humanity’s Last Exam
- 44%
- CritPt
- 25%
- AA-Omniscience
- 63%
- AA-LCR
- 84%
Similar models
- GPT-6 Sol (xhigh)OpenAIQuality Score 61.5Value Score 40.0
- GPT-5.6 Sol (high)OpenAIQuality Score 62.3Value Score 36.3
- GPT-5.6 Sol (medium)OpenAIQuality Score 60.8Value Score 34.4
- GPT-5.6 Sol (xhigh)OpenAIQuality Score 63.2Value Score 37.4
- GPT-6 Sol (medium)OpenAIQuality Score 59.5Value Score 37.3
- GPT-6 Sol (max)OpenAIQuality Score 63.3Value Score 42.2