readable AI benchmarks (simplified)
OpenAI
GPT-6.1 Terra (Max)
GPT-6.1 Terra (Max) has a Quality Score of 69.5, ranking 27th among 398 scored models. Per 1M tokens, pricing is $1.00 input, $5.00 output, $0.050 cached input, and $1.25 cache write. It accepts text, image, and pdf input, outputs text, and has a 1M token context window. Its Reliability Score is 64.9, ranking 30th among 399 scored models, above average (total average: 38.2). Its Value Score is 50.4, high compared with the total Value average of 33.7.
Quality Score69.5coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score50.4
Factual reliability64.9
Cache Discount95%
Model specification
- Reasoning
- reasoning
- Input modalities
- text, image, pdf
- Output modalities
- text
- Context window
- 1M tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $1.00
- Output
- $5.00
- Cached Input
- $0.050
- Cache write
- $1.25
- Cost per task
- $0.403
Capability
- Intelligence
- 48.1
- Coding
- not available
- Agentic
- not available
- Omniscience
- 29.8
- Correct
- 49.1%
- Blended price
- $0.735
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 68.5%
Correct 49.1%Incorrect 19.4%Partial / not attempted 31.5%
Artificial Analysis benchmarks
- SciCode
- 55%
- Humanity’s Last Exam
- 46%
- CritPt
- 28%
- AA-Omniscience
- 65%
- AA-LCR
- 83%
Similar models
- GPT-6 Astra (Low)OpenAIQuality Score 70.4Value Score 38.9
- GPT-6.1 Sol (Medium)OpenAIQuality Score 71.7Value Score 47.9
- GPT-6.1 Terra (Xhigh)OpenAIQuality Score 67.1Value Score 48.7
- GPT-6 Astra (Medium)OpenAIQuality Score 73.7Value Score 40.7
- GPT-6.1 Sol (High)OpenAIQuality Score 74.0Value Score 49.4
- GPT-6 Sol (Xhigh)OpenAIQuality Score 65.7Value Score 43.6