readable AI benchmarks (simplified)
SpaceXAI
Grok 4.7 (high)
Grok 4.7 (high) has a Quality Score of 62.0, ranking 22nd among 264 scored models. It has a 500k token context window. Its Reliability Score is 65.5, ranking 17th among 264 scored models, above average (total average: 35.4).
Quality Score62.0coverage 78.8%: missing Epoch General ECI, Coding, CursorBench 3.2, Agentic and DeepSWE v1.1
Value Scorenot available
Reliability65.5
Cache Discountnot available
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 500k tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- not available
- Output
- not available
- Cached Input
- not available
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 46.3
- Coding
- not available
- Agentic
- not available
- Omniscience
- 30.9
- Correct
- 47.8%
- Blended price
- not available
Answer outcomes
Attempt rate: 64.7%
Correct 47.8%Incorrect 16.9%Abstained 35.3%
Artificial Analysis benchmarks
- GDPval-AA v2
- 60%
- SciCode
- 58%
- Humanity’s Last Exam
- 42%
- CritPt
- 18%
- AA-Omniscience
- 65%
- AA-LCR
- 77%
Similar models
- Grok 4.7 (xhigh)SpaceXAIQuality Score 62.3Value Score not available
- Grok 4.6 (high)SpaceXAIQuality Score 62.1Value Score 39.8
- Grok 4.6 (xhigh)SpaceXAIQuality Score 60.6Value Score 38.6
- Grok 4.6 (medium)SpaceXAIQuality Score 59.4Value Score 37.4
- Grok 4.6 (low)SpaceXAIQuality Score 56.1Value Score 32.8
- GPT-5.6 Sol (xhigh)OpenAIQuality Score 63.2Value Score 37.4