Inkling 2 Small beats GLM 5.3 at half the cost on DeepFinance benchmark
cHHillee · x · 2026-11-07
Thinky Machines' Inkling 2 Small pushes the cost-performance pareto frontier for open source models on DeepFinance bench. On long-horizon finance workflows it scores higher than GLM 5.3 at 50% of the cost, and nearly matches Qwen 3.8 Max at just 11% of the cost. It also outperforms DeepSeek V4.1 Flash and Nvidia's Nemotron 3 Ultra, making it the best American open source model on the benchmark.
Related event: Inkling 2 Small Pushes Open-Model Frontier in Code and Finance(2 posts)→
More from Models
- Dev observes Opus 5.5 picking a completely random test secret — davidcrawshaw · 2026-11-09
- Dev says Opus 5.5 degraded: a game he once built in 2 prompts is now impossible — Rasmic · 2026-11-09
- SuperGrok $100-tier user hits usage wall on a Qwen 27B query, threatens to cancel — gnukeith · 2026-11-09
- Tsinghua & Moonshot's TCSExam: GPT-6 Astra proves 70% of theorems, solves 0 open conjectures — rohanpaul_ai · 2026-11-09
- TCSExam benchmark: GPT-6 Astra tops Full at 71.9, Opus 5.5 leads Lite at 72.3 — rohanpaul_ai · 2026-11-09
- Internal benchmark chart fuels speculation Anthropic and OpenAI are a generation ahead internally — haider1 · 2026-11-09