BenchAtlas

Rankings / DeepSeek

R1

released 2025-01-22

BenchAtlas Index

as of 2026-07-14
Not enough benchmark coverage for a composite score (needs ≥4 families across ≥3 categories). The per-benchmark evidence below stands on its own — sparse coverage is an evidence gap, not a low score.

Benchmark evidence

6 results
reasoning math
ARC-AGI-1older version
split=semi_private · model_type=CoT
15.8 %independentARC Prize Leaderboard
ARC-AGI-2
split=semi_private · model_type=CoT
1.3 %independentARC Prize Leaderboard
ARC-AGI-2
split=public_eval · model_type=CoT
0.3 %independentARC Prize Leaderboard
ARC-AGI-2
split=semi_private · model_type=CoT
0.1 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-2
split=public_eval · model_type=CoT
0.1 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-1older version
split=semi_private · model_type=CoT
0.1 usd_per_taskindependentARC Prize Leaderboard