readable AI benchmarks (simplified)
SpaceXAI
Grok 4
Grok 4 has a Quality Score of 42.8, ranking 145th among 551 scored models. Per 1M tokens, pricing is $3.00 input and $15.00 output. It has a 256k token context window. Its Reliability Score is 51.0, ranking 99th among 553 scored models, above average (total average: 35.6).
Quality Score42.8coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability51.0
Cache Discountnot available
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 256k tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $3.00
- Output
- $15.00
- Cached Input
- not available
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 22.5
- Coding
- not available
- Agentic
- not available
- Omniscience
- 2.1
- Correct
- 40.5%
- Blended price
- not available
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 78.9%
Correct 40.5%Incorrect 38.4%Partial / not attempted 21.1%
Artificial Analysis benchmarks
- Humanity’s Last Exam
- 27%
- GPQA Diamond
- 88%
- CritPt
- 2%
- AA-Omniscience
- 51%
- AA-LCR
- 68%
Similar models
- Grok 4.3 (low)SpaceXAIQuality Score 47.2Value Score 34.8
- Grok 4.20 0309 (Reasoning)SpaceXAIQuality Score 47.6Value Score 32.8
- Grok 4.3 (medium)SpaceXAIQuality Score 48.2Value Score 35.6
- Grok 4.3 (high)SpaceXAIQuality Score 48.6Value Score 35.9
- Grok Build 0.1 0616SpaceXAIQuality Score 47.5Value Score 35.8
- Grok 4.20 0309 v2 (Reasoning)SpaceXAIQuality Score 48.4Value Score 35.8