Gemini 4 Neon leads finance eval with ~68% fewer output tokens than Fable 5.2
echen · x · 2026-11-20
Surge AI shared details from DAYJOB: Finance, an 80-task benchmark covering credit memos, valuation models, covenant tests, and stress tests. Gemini 4 Neon scored 50.5%, beating GPT 6.2 Astra (45.8%) and Claude Fable 5.2 (43.7%), while generating just 205K output tokens versus Fable's 644K — roughly one-third the tokens for a higher success rate.
Related event: Gemini 4 Neon Tops Surge Finance Benchmark at Far Lower Cost Than Claude(2 posts)→
More from Models
- Tesla FSD 15's real-time view isn't 3D rendering — it's the AI model's own synthetic perception — mark_k · 2026-11-22
- Gemini Black Friday half-price: JP-region trick gets Pro annual plan for $91.54 — huangyun_122 · 2026-11-22
- Microsoft's USB4 RDMA lets mini PCs pool memory to run Qwen3-235B — JFPuget · 2026-11-22
- Google AI Mode now enforces usage limits, users surprised by rate-limit popup — elvano124 · 2026-11-22
- Sol 6.2 now refuses reverse engineering that Sol 6.1 happily did for a month — cardak98 · 2026-11-22
- Anthropic's record ~$81B IPO, GPT-6.2 pricing, Qwen4-Max and Copilot Autopilot: week in review — ksraj1001 · 2026-11-22