Inkling Tops ARC Open-Weight Leaderboard
GregKamradt · x · 2026-07-18
ARC Prize announced Inkling's evaluation results on ARC-AGI, calling it the highest-scoring open-weight model to date on both ARC-AGI-1 and ARC-AGI-2.
Specific scores:
- ARC-AGI-2: 36.5% at $0.64/task
- ARC-AGI-1: 79.5% at $0.30/task
This update focuses purely on an open-weight model's current benchmark ranking and task costs rather than introducing a new methodology.
Related event: Inkling Tops ARC-AGI Leaderboard for Open-Weight Models(2 posts)→
More from Models
- Nanbeige4.3-33B benchmarked: 59 tok/s single stream, ~1,060 tok/s across 64 concurrent runs — MaziyarPanahi · 2026-10-26
- Only 2 of 25 full ChatGPT rewrites flagged 100% AI by detectors — paulnovosad · 2026-10-26
- Qwen 4 Reportedly Spotted in the Arena, Hints at Alibaba's Next-Gen Model Testing — AIFlow_ML · 2026-10-26
- Nathan Lambert's first open models lecture: distillation, risks and the ecosystem explained — natolambert · 2026-10-26
- Nanbeige 4.3-33B flops real-world test: zero compilable output vs Qwen — julianharris · 2026-10-26
- Claude's safety classifier blocks SS7 defense research, pushing a security dev to an abliterated GLM — l4rz · 2026-10-26