ARC Prize Adds Model Comparison, Gemini 3.7 Flash Scores High
mhmazur · x · 2026-08-21
ARC Prize rolled out a feature to make it easier to compare models directly on results pages.
Gemini 3.7 Flash Performance:
- ARC-AGI-1 Semi-Private: High effort score 95.5% ($0.12/task)
- ARC-AGI-2 Semi-Private: High effort score 84.6% ($0.25/task)
- Scores for Medium and Low efforts are also listed.
Users can now view and compare specific model variants side-by-side.
More from Models
- Musk Confirms Work to Improve Grok's Writing Skills — mark_k · 2026-08-21
- Why 'Full Pass Rate' is a flawed metric for LLM evaluation — xeophon · 2026-08-21
- Anthropic's Fable Breaks RareBench Record After Relaxing Filters — danielmckinn0n · 2026-08-21
- NVIDIA Explains Omni-Models: Unified Architecture for Text, Images, Audio, Video, and Actions — NVIDIA Developer · 2026-08-21
- Monitors Detect Significant Behavior Shift in Claude Opus — altryne · 2026-08-21
- Users report GPT-4.1 Sol model suddenly became dumb with irrelevant answers — M-M103 · 2026-08-21