Gemini 3.7 Flash Tops AI Analyst Benchmark with Fastest Speed
vedantmisra · x · 2026-08-21
Gemini 3.7 Flash achieved the #1 spot on the Artificial Analysis AA-AnalystAgent benchmark. This benchmark evaluates models on 80 real-world quantitative analysis tasks across 14 domains (finance, healthcare, hydrology, government appropriations) within an isolated Python 3.12 sandbox. Models must use libraries like pandas and polars to process spreadsheets and documents.
Key results for Gemini 3.7 Flash:
- Accuracy: Ranked #1 with 60.0% pass@5 (70.5% pass@1), significantly outperforming Fable and GPT-5.6.
- Speed: Fastest among tested models at 1.32s per task.
- Cost: $0.54 per task (indicating high efficiency).
Related event: Gemini 3.7 Flash Tops AA-AnalystAgent Benchmark(5 posts)→
More from Models
- NVIDIA releases Qwen3.8-Flash-Next FP4 local model with new lossless compression format — TheZachMueller · 2026-10-16
- Are the fastest GPU kernels now written by AI? Kernels are hyper-verifiable, argues one dev — fleetwood___ · 2026-10-16
- Scale AI launches muse spark open: 816B-param MoE with 1M context, billed as top US open-weight model — jiayi_pirate · 2026-10-16
- NVIDIA HF listing for Qwen3.8-Flash-Next-FP4-Local leaks unannounced Qwen3.8 model — TheZachMueller · 2026-10-16
- Muse Spark Open, billed as the most capable US open-weight model, lands on Nebius day one — Arindam_1729 · 2026-10-16
- Model at capacity for a straight week drives frustrated dev back to Opus — joonasvirtanen · 2026-10-16