Gemini 3.6 Flash Tops FrontierFinance Benchmark at $2.41/Query
tulseedoshi · x · 2026-07-31
In the FrontierFinance open benchmark for finance AI agents by Samaya AI, Gemini 3.6 Flash scored 46.3%, beating Claude Opus 4.8 and tying with GPT-5.6 Sol.
While delivering frontier-level accuracy, the model is highly efficient: it costs only $2.41 per query and runs in 164 seconds, making it cheaper and faster than peers of the same tier.
Analysis indicates that Gemini 3.6 Flash is notably better than Opus 4.8 at surfacing qualitative and contextual insights. It also leads in Screening & Discovery, the benchmark's hardest use case, making it ideal for financial applications requiring a balance of speed, cost-efficiency, and high performance.
Related event: Gemini 3.6 Flash Tops Financial AI Benchmark(2 posts)→
More from Models
- Why are sub-15B open models so rare now? Labs seem to have settled on 24-27B minimum — Hot_Example_4456 · 2026-10-16
- User spots model openly generating "ideal responses" to train other models — liminal_bardo · 2026-10-16
- Reflection's 501B MoE Beam hits 463 tok/s on 8x GB200 with NVFP4 at day 0 — zhyncs42 · 2026-10-16
- Gemma 4 31B QAT on one 24GB card: 46 tok/s plain, ~80 with draft model on RTX 4090 — Subject_Poet_3861 · 2026-10-16
- JevBench v1.7.46 leaderboard: new d1-ultra tops 32 API systems at 76.1 composite — airesearch12 · 2026-10-16
- Team of 5 mulls dropping ChatGPT Pro for Business as OpenAI quota parity stays unclear — bettercallfool · 2026-10-16