readable AI benchmarks (simplified)
OpenAI
GPT-5.5 (xhigh)
GPT-5.5 (xhigh) has a Quality Score of 67.6, ranking 10th among 53 scored models. Per 1M tokens, pricing is $5.00 input, $30.00 output, and $0.500 cached input. Its Reliability Score is 60.0, ranking 10th among 53 scored models, above average (total average: 50.1). Its Value Score is 41.5, around average compared with the total Value average of 39.6.
Quality Score67.6coverage 93.8%: missing Epoch General ECI and DeepSWE v1.1
Value Score41.5
Reliability60.0
Cache Discount90%
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- not available
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $5.00
- Output
- $30.00
- Cached Input
- $0.500
- Cache write
- not available
- Cost per task
- $0.992
Capability
- Intelligence
- 54.8
- Coding
- 74.9
- Agentic
- 44.9
- Omniscience
- 20.1
- Correct
- 56.9%
- Blended price
- $4.35
Answer outcomes
Attempt rate: 93.8%
Correct 56.9%Incorrect 36.9%Abstained 6.2%
Artificial Analysis benchmarks
- GDPval-AA v2
- 50%
- τ³-Banking
- 31%
- Terminal-Bench v2.1
- 84%
- SciCode
- 56%
- Humanity’s Last Exam
- 44%
- GPQA Diamond
- 94%
- CritPt
- 27%
- AA-Omniscience
- 60%
- AA-LCR
- 74%
Similar models
- GPT-5.6 Sol (medium)OpenAIQuality Score 67.2Value Score 40.7
- GPT-5.6 Sol (high)OpenAIQuality Score 69.5Value Score 42.1
- GPT-5.5 (high)OpenAIQuality Score 66.0Value Score 40.3
- GPT-5.6 Terra (max)OpenAIQuality Score 62.5Value Score 43.3
- GPT-5.6 Sol (xhigh)OpenAIQuality Score 71.1Value Score 43.2
- GPT-5.5 (medium)OpenAIQuality Score 63.4Value Score 38.7