Vals Index GDP-weighted chart: Sonnet 5.5 tops accuracy, GPT-6.1 Sol leads the efficiency frontier
allenainie · x · 2026-10-29
A circulating "Vals Index" GDP-weighted benchmark plots models on accuracy vs cost: Claude Sonnet 5.5 leads on accuracy, Gemini 4 Carbon anchors the efficient frontier, GPT-6.1 Sol stands out on value, with DeepSeek V4.1 Flash 1017 and Xiaomi MiMo V2.6 Pro/Flash in the low-cost zone. The chart filters by open weights, accuracy and cost.
Related event: Vals AI Index: Claude Sonnet 5.5 Tops GDP-Weighted Leaderboard(2 posts)→
More from Models
- Rumor: OpenAI pushes big release to tomorrow, possibly due to Gemini 4 Carbon — mark_k · 2026-10-29
- Gemini 4.0 Carbon's security praised, but mocked for losing the "felony bench" — vitaliychiley · 2026-10-29
- Google hits frontier on private benchmarks yet stock plunges 8% after hours — bookwormengr · 2026-10-29
- Dev praises gpt-6-luna's price-performance, calls opus-5.5 best for implementation — emax · 2026-10-29
- Meta researcher marvels at Gemini's progress in under 6 months, sharing a suspicious leaderboard — armandjoulin · 2026-10-29
- AA-PersonalityBench: GPT-6 and Grok are the most direct models, Gemini 4 ranks last — ArtificialAnlys · 2026-10-29