AI Benchmark Model
Agnes 3.0 Flash
Benchmark scores, pricing, speed, and model comparisons for Agnes 3.0 Flash.
Key scores
Agnes 3.0 Flash is an artificial intelligence model developed by Sapiens AI and released on September 11, 2026. The model maintains an intelligence index of 35.5. In standardized performance evaluations, Agnes 3.0 Flash achieved a GPQA score of 0.924, an HLE score of 0.385, a SciCode score of 0.516, and an LCR score of 0.81. Regarding operational efficiency, the model provides an output speed of 228.976 tokens per second with a time to first token of 1.197 seconds. Pricing for the model is structured at $0.05 per million input tokens and $0.15 per million output tokens, resulting in a blended rate of $0.07 per million tokens for users.
Benchmark results
4 tracked benchmark rows for Agnes 3.0 Flash.
GPQA Reasoning
92.4% LCR Other
81.0% SciCode Other
51.6% HLE Other
38.5%