Cloudflare Clef Release - ARC-Challenge · accuracy: leaderboard

Decision Index 0.2.1 suite, Cloudflare internal run (card: "Per-benchmark results from our internal run of the Decision Index 0.2.1 suite"); decision-kit renditions, not generic benchmark protocols; announcement blog: "Across the 43 eval benchmarks that we ran" not stated Name boards exactly like the ten existing clef_multimodal_release boards; put "Decision Index 0.2.1 internal run" in the protocol so the rows are never fused with generic BFCL/GPQA/MMLU boards or with Decision Index 0.3/0.4.1 boards. Metric: accuracy.

Metric: accuracy. Source: huggingface.co. Saturation forecast: Rough model projection: around 2026. 2 models tracked. Updated 14 Nov 2026.

Top models

#ModelScoreOverall rank
1Clef flash 9.5B98.3
2Clef 27B97.7

Interactive version: theaggregate.ai/benchmark?slug=cloudflare-clef-release-arc-challenge-accuracy · How It Works · Data refreshed daily, snapshot 2026-11-16.