readable AI benchmarks (simplified)
OpenAI
GPT-5.2 Codex (xhigh)
GPT-5.2 Codex (xhigh) has a Quality Score of 46.4, ranking 121st among 551 scored models. Per 1M tokens, pricing is $1.75 input, $14.00 output, and $0.175 cached input. It accepts text, image, and pdf input, outputs text, and has a 400k token context window. Its Reliability Score is 48.9, ranking 126th among 553 scored models, above average (total average: 35.6). Its Value Score is 30.1, around average compared with the total Value average of 30.7.
Quality Score46.4coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score30.1
Factual reliability48.9
Cache Discount90%
Model specification
- Reasoning
- reasoning
- Input modalities
- text, image, pdf
- Output modalities
- text
- Context window
- 400k tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $1.75
- Output
- $14.00
- Cached Input
- $0.175
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 28.5
- Coding
- not available
- Agentic
- not available
- Omniscience
- -2.2
- Correct
- 41.1%
- Blended price
- $1.87
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 84.3%
Correct 41.1%Incorrect 43.2%Partial / not attempted 15.7%
Artificial Analysis benchmarks
- Humanity’s Last Exam
- 36%
- GPQA Diamond
- 90%
- CritPt
- 9%
- AA-Omniscience
- 49%
- AA-LCR
- 82%
Similar models
- GPT-6 Luna (medium)OpenAIQuality Score 46.4Value Score 42.4
- GPT-5.6 Terra (medium)OpenAIQuality Score 46.9Value Score 30.7
- GPT-5.4 (low)OpenAIQuality Score 47.4Value Score 30.2
- GPT-5.5 Instant (June 2026)OpenAIQuality Score 45.9Value Score 27.0
- GPT-5.2 (medium)OpenAIQuality Score 45.5Value Score 29.5
- GPT-5.6 Luna (high)OpenAIQuality Score 46.7Value Score 39.9