readable AI benchmarks (simplified)
Nanbeige
Nanbeige4.3-33B
Nanbeige4.3-33B has a Quality Score of 34.1, ranking 125th among 229 scored models. It has a 524,288 token context window. Its Reliability Score is 47.8, ranking 115th among 238 scored models, above average (total average: 46.2).
Quality Score34.1coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability47.8
Cache Discountnot available
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 524,288 tokens
- Weights
- open 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
- 20.4
- Omniscience (native net)
- -4.4
- Correct
- 11.7%
- Blended price
- not available
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 27.7%
Correct 11.7%Incorrect 16.1%Partial / not attempted 72.3%
Artificial Analysis benchmarks aa-v5
Current Intelligence Index components
- AA-Briefcase v1.1
- 1161.8 Elo
- AutomationBench-AA
- 53.1% private 657-task split from dataset v1.0.6
- GDP.pdf
- 11.2%
- FrontierCode v2.0
- 10.7% AA Stirrup · 132 tasks, 3 attempts per task
- Terminal-Bench v4.0
- 29.8% AA mini-swe-agent standardized runs · 66 tasks, pass@1 averaged over 3 repeats per task
- AA-Omniscience v1.1
- -4.4 native net
- HLE-Diamond
- 6.9%
- CritPt v2 Hard
- 15.5% AA Stirrup · hard subset, 40 of 70 problems
- Terminal-Bench-Science v0.1.0
- 1.0%
Similar models
- Nanbeige4.1-3BNanbeigeQuality Score not availableValue Score not available
- Qwen3.8 27B (Xhigh)AlibabaQuality Score 33.5Value Score 25.6
- Claude 4 Sonnet (Reasoning)AnthropicQuality Score 34.5Value Score not available
- Claude 4.5 Sonnet (Reasoning)AnthropicQuality Score 35.3Value Score 22.3
- GPT-5 (Low)OpenAIQuality Score 32.7Value Score 22.1
- GPT-5 mini (Medium)OpenAIQuality Score 32.5Value Score 26.6