Surge AI launches Tuesday Frontier Work Index, 8 benchmarks in one score
echen · x · 2026-08-19
Surge AI launched Tuesday: The Frontier Work Index, built on the premise that professional intelligence isn't one thing. It combines 8 benchmarks into a single score:
- Components: Chartography (chart reading), HANDBOOK.md, GDP.pdf, ComplexConstraints, CoreCraft, Hemingway-bench (readability), Antidote, and Riemann-bench, with more planned.
- Philosophy: it tests the floor (instruction following, context, tool use), the ceiling (creative reasoning on hard problems), and soft skills — judgment and taste, since nobody wants a perfectly reasoned but dense report.
Top leaderboard entries include GPT 5.6 Sol Max at 66.7, Claude Opus 5 Adaptive/Max at 66.5, Grok 4.6 xHigh at 62.4, DeepSeek V4 Pro at 59.7, and Qwen 3.8 Max at 58.7, spanning OpenAI, Anthropic, xAI, Google, DeepSeek, Meta, Moonshot, Zhipu and Alibaba models across reasoning settings.
Related event: Surge AI Launches Tuesday Work Index; Fable 5 Edges Out GPT 5.6 Sol(7 posts)→
More from Models
- GLM 5.5 rumored to drop soon, coding ability expected to match frontier models — bindureddy · 2026-10-16
- Five rounds of adversarial prompting make Opus 5.5 and Argon converge on identical output — LanceCharger · 2026-10-16
- DIY benchmark ranks 18 models on subjective judgments, GLM-5.3 tops consensus match — arkuto · 2026-10-16
- Bindu Reddy: Google's Argon excels at complex doc writing at half the cost of Opus — bindureddy · 2026-10-16
- MAI-2 is 2x bigger than V4-Pro while V4.1F is 3x smaller: Microsoft's scaling ladder questioned — teortaxesTex · 2026-10-16
- Step 5 Preview hits DeepInfra day-zero: 600B MoE, 1M context, $1/M input tokens — StepFun_ai · 2026-10-16