readable AI benchmarks (simplified)
Sapiens AI
Agnes 3.0 Flash
Agnes 3.0 Flash has a Quality Score of 49.7, ranking 32nd among 139 scored models. Per 1M tokens, pricing is $0.050 input, $0.150 output, and $0.0050 cached input. It has a 1M token context window. Its Reliability Score is 44.7, ranking 57th among 139 scored models, above average (total average: 40.0). Its Value Score is 47.7, high compared with the total Value average of 30.0.
Quality Score49.7coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score47.7
Factual reliability44.7
Cache Discount90%
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 1M tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $0.050
- Output
- $0.150
- Cached Input
- $0.0050
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 35.5
- Coding
- not available
- Agentic
- not available
- Omniscience
- -10.6
- Correct
- 25.5%
- Blended price
- $0.029
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 61.5%
Correct 25.5%Incorrect 36.1%Partial / not attempted 38.5%
Artificial Analysis benchmarks
- GDPval-AA v2
- 53%
- τ³-Banking
- 48%
- SciCode
- 52%
- Humanity’s Last Exam
- 38%
- GPQA Diamond
- 92%
- CritPt
- 15%
- AA-Omniscience
- 45%
- AA-LCR
- 81%
Similar models
- Agnes 2.5 Pro Alpha (based on Qwen3.5 397B A17B)Sapiens AIQuality Score 39.3Value Score 33.4
- Agnes 2.5 Pro BetaSapiens AIQuality Score not availableValue Score not available
- GPT-5.6 Luna (Xhigh)OpenAIQuality Score 48.9Value Score 41.8
- DeepSeek V4 Flash (high)DeepSeekQuality Score 48.2Value Score 44.2
- Claude Sonnet 5 (Xhigh)AnthropicQuality Score 52.2Value Score 34.7
- Claude Sonnet 5 (High)AnthropicQuality Score 48.4Value Score 32.2