High-throughput Flash model for scaled agentic search and document processing, with 350 output tokens per second reported by Artificial Analysis.
| Benchmark | Score | Rank |
|---|---|---|
aaAgentic | 26.8% | #16 / 16 |
AA Intelligence Independent composite of agentic work, coding, scientific reasoning, and general capability | 36.5% | #22 / 22 |
AA Coding Independent composite of implementation, terminal use, and real-codebase agent performance | 49.3% | #22 / 22 |
MMMUvals.ai College-level multimodal reasoning across 30+ disciplines | 83.6% | #29 / 51 |
MMLU-Provals.ai Harder 10-option successor to MMLU; more reasoning-focused | 85.8% | #42 / 61 |
LiveCodeBenchvals.ai Contamination-free competitive programming (filtered by cutoff date) | 79% | #47 / 62 |
GPQAArtificial Analysis PhD-level science questions even experts struggle with | 83.8% | #64 / 95 |
hleArtificial Analysis | 18.8% | #65 / 85 |