Anthropic's Claude 5 flagship. New ARC-AGI-2 state of the art at 97.1%, and the first model to post a meaningful ARC-AGI-3 score (30.2%).
| Benchmark | Score | Rank |
|---|---|---|
MMLU-Provals.ai Harder 10-option successor to MMLU; more reasoning-focused | 91.6% | #1 / 51 |
MMMUvals.ai College-level multimodal reasoning across 30+ disciplines | 89.9% | #1 / 51 |
ARC-AGIARC Prize Novel reasoning tasks requiring fluid intelligence | 97.1% | #1 / 27 |
AA Intelligence Independent composite of agentic work, coding, scientific reasoning, and general capability | 60.7% | #1 / 11 |
aaAgentic | 55.3% | #1 / 5 |
LiveCodeBenchvals.ai Contamination-free competitive programming (filtered by cutoff date) | 89% | #2 / 53 |
AA Coding Independent composite of implementation, terminal use, and real-codebase agent performance | 78% | #2 / 11 |
hleArtificial Analysis | 52.6% | #2 / 66 |
GPQAArtificial Analysis PhD-level science questions even experts struggle with | 93.2% | #7 / 78 |