Enterprise benchmark: GPT 6.1 Sol High scores 94.8% at $1.07 per task, DeepSeek 1017 78.1% at $0.42
emilahlback · x · 2026-10-27
emilahlback ran OpenAI's newly released models through EnergyBench, an enterprise benchmark plotting task score against cost per task:
- GPT 6.1 Sol (High): 94.8% at $1.067 per task — top quality, highest cost
- GPT 6.1 Sol (Medium): 90.6% at $0.831
- DeepSeek 1017: 78.1% at $0.422
- GPT 6.1 Terra: 62.7% at $0.280
- GPT 6 Luna Max (previous gen): 43.0% at $0.117
The chart highlights the quality-cost tradeoff: Sol leads on accuracy at over twice DeepSeek's per-task cost, while Terra sits in the budget tier with a large quality gap versus its sibling.
More from Models
- Open-weight model poisoning and sleeper-agent risk gain attention — ianand · 2026-10-27
- GPT-6.1 Terra matches GPT-6 Astra at 57.6% on Agents' Last Exam at 1/16.6x cost — aakashgupta · 2026-10-27
- Cloudflare's Clairic: a System One extraction model returning typed values with confidence scores — omarsar0 · 2026-10-27
- Asking an AI About Leaks: First "Surely Fake", Then Slowly Convinced — johnowhitaker · 2026-10-27
- Princeton's PaperScorer fine-tunes Qwen to predict paper acceptance, hitting 77.5% accuracy — IanArawjo · 2026-10-27
- Share prompts, not code: a reusable prompt suite for evaluating small models (4B-36B) — yaroslavvb · 2026-10-27