readable AI benchmarks (simplified)
Joy Future Academy
JoyAI-VL-Preview
JoyAI-VL-Preview has a Quality Score of 36.5, ranking 139th among 283 scored models. Per 1M tokens, pricing is $0.0000 input and $0.0000 output. It has a 1,048,576 token context window. Its Reliability Score is 45.0, ranking 167th among 288 scored models, below average (total average: 48.2).
Quality Score36.5coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability45.0
Cache Discountnot available
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 1,048,576 tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $0.0000
- Output
- $0.0000
- Cached Input
- not available
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 28.0
- Omniscience (native net)
- -9.9
- Correct
- 33.5%
- Blended price
- not available
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 77.0%
Correct 33.5%Incorrect 43.5%Partial / not attempted 23.0%
Artificial Analysis benchmarks aa-v5
Current Intelligence Index components
- AA-Briefcase v1.1
- 1462.7 Elo
- AutomationBench-AA
- 61.7% private 657-task split from dataset v1.0.6
- GDP.pdf
- 20.6%
- FrontierCode v2.0
- 19.0% AA Stirrup · 132 tasks, 3 attempts per task
- Terminal-Bench v4.0
- 23.2% AA mini-swe-agent standardized runs · 66 tasks, pass@1 averaged over 3 repeats per task
- AA-Omniscience v1.1
- -9.9 native net
- HLE-Diamond
- 26.7%
- CritPt v2 Hard
- 32.0% AA Stirrup · hard subset, 40 of 70 problems
- Terminal-Bench-Science v0.1.0
- 3.8%
Similar models
- GPT-6 Luna (Max)OpenAIQuality Score 36.9Value Score 33.7
- Qwen3.8-Flash-NextAlibabaQuality Score 36.2Value Score 32.8
- Claude Sonnet 5 (Medium)AnthropicQuality Score 37.3Value Score 24.8
- MiMo-V2.6-FlashXiaomiQuality Score 35.7Value Score 33.2
- MiniMax-M3.1-FlashMiniMaxQuality Score 37.9Value Score 34.0
- DeepSeek V4 Pro 0424 (High)DeepSeekQuality Score 37.4Value Score 31.9