RuneBench Cost-Efficiency Data: Hy4 High Hits 6.23 at $0.59 per Run, a Pareto Frontier Point
mariofilhoml · x · 2026-11-12
Developer mariofilhoml shared cost-efficiency measurements on RuneBench, with a scatter chart of score vs. average API cost per run:
- Hy4 High (inside Pi): 6.23 score at $0.59/run — an unofficial Pareto frontier point
- Hy4 High on OpenCode 1.19: 4.92 at $0.36/run
- The chart also plots dozens of models including GPT-6 variants, Opus 5.x, Gemini 4 Argon, Kimi K3.1 Pro, Grok 4.7, and GLM 5.3; DS V4.1 Flash 1017 and GLM 5.3 Flash sit in the cheap-and-strong region
The author offered to share data with RuneBench creator maxbittker for official validation and plans to test DS 1017 on DSH minimal next.
More from Models
- Microsoft's MAI Transcribe 2 sees 12x usage growth, hitting 8.5M weekly transcriptions — mustafasuleyman · 2026-11-12
- Focus less on using the best model, more on using the model best — daniel_mac8 · 2026-11-12
- YC F26 Startup agenticdataco Launches Real-World Speech Data and Audio-Native RL Environments — ycombinator · 2026-11-12
- Microsoft's diagnostic AI solves 83% of NEJM cases vs 36% for physicians — PeterDiamandis · 2026-11-12
- Petition demands OpenAI permanently keep ChatGPT Standard Voice Mode and all 9 voices — shaunralston · 2026-11-12
- Researcher praising uncensored Kimi 3.1 Pro gets his X account hacked — erikphoel · 2026-11-12