readable AI benchmarks (simplified)
Google
Gemini 4 Carbon (High)
Gemini 4 Carbon (High) has a Quality Score of 84.1, ranking 1st among 216 scored models. Per 1M tokens, pricing is $4.00 input, $20.00 output, $0.200 cached input, and $4.00 cache write. It has a 1M token context window. Its Reliability Score is 76.8, ranking 1st among 228 scored models, above average (total average: 46.1). Its Value Score is 51.7, high compared with the total Value average of 33.8.
Quality Score84.1coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score51.7
Factual reliability76.8
Cache Discount95%
Model specification
- Reasoning
- 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
- $0.200
- Cache write
- $4.00
- Cost per task
- $7.76
Capability
- Intelligence
- 59.4
- Coding
- not available
- Agentic
- not available
- Omniscience
- 53.5
- Correct
- 58.3%
- Blended price
- $2.94
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 63.0%
Correct 58.3%Incorrect 4.8%Partial / not attempted 37.0%
Artificial Analysis benchmarks
- SciCode
- 64%
- Humanity’s Last Exam
- 60%
- CritPt
- 36%
- AA-Omniscience
- 77%
- AA-LCR
- 79%
Similar models
- Gemini 4 Argon (High)GoogleQuality Score 75.3Value Score 46.3
- Gemini 3.7 Flash (Medium)GoogleQuality Score 61.4Value Score 45.9
- Gemini 3.7 Flash (Low)GoogleQuality Score 59.0Value Score 44.1
- Gemini 3.5 Flash (Medium)GoogleQuality Score 56.1Value Score 38.0
- Gemini 3.8 Flash (High)GoogleQuality Score 54.3Value Score 40.6
- Gemini 3.8 Flash (Medium)GoogleQuality Score 54.0Value Score 40.4