readable AI benchmarks (simplified)
SpaceXAI
Grok 4.20 0309 v2 (Non-reasoning)
Grok 4.20 0309 v2 (Non-reasoning) has a Quality Score of 20.9, ranking 197th among 238 scored models. Per 1M tokens, pricing is $1.25 input, $2.50 output, and $0.200 cached input. It accepts text, image, and pdf input, outputs text, and has a 2M token context window. Its Reliability Score is 27.7, ranking 204th among 245 scored models, below average (total average: 46.4). Its Value Score is 15.5, low compared with the total Value average of 28.3.
Quality Score20.9coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score15.5
Factual reliability27.7
Cache Discount84%
Model specification
- Reasoning
- non-reasoning
- Input modalities
- text, image, pdf
- Output modalities
- text
- Context window
- 2M tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $1.25
- Output
- $2.50
- Cached Input
- $0.200
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 14.2
- Omniscience (native net)
- -44.6
- Correct
- 26.7%
- Blended price
- $0.640
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 98.0%
Correct 26.7%Incorrect 71.3%Partial / not attempted 2.0%
Artificial Analysis benchmarks legacy records
- Humanity’s Last Exam
- 28%
- GPQA Diamond
- 78%
- CritPt
- 0%
- AA-LCR
- 23%
Similar models
- Grok 4.20 0309 (Non-reasoning)SpaceXAIQuality Score 21.7Value Score 14.9
- Grok 4.3 (Non-reasoning)SpaceXAIQuality Score 23.7Value Score 17.5
- Grok 4 Fast (Reasoning)SpaceXAIQuality Score 26.5Value Score not available
- Grok 4.1 Fast (Reasoning)SpaceXAIQuality Score 27.7Value Score not available
- Grok 4.3 (Low)SpaceXAIQuality Score 40.6Value Score 30.0
- Grok 4.3 (Medium)SpaceXAIQuality Score 41.6Value Score 30.7