First Sonnet of the Claude 5 generation. Terminal-Bench 2.1 80.4% and GDPval-AA v2 parity with Opus 4.8 (1618 vs 1615) at Sonnet-tier cost.
| Benchmark | Score | Rank |
|---|---|---|
OSWorld Computer use in real desktop environments | 81.2% | #1 / 13 |
Terminal Agentic terminal coding tasks requiring multi-step execution | 80.4% | #6 / 56 |
hleArtificial Analysis | 39.6% | #22 / 76 |
MMLU-Provals.ai Harder 10-option successor to MMLU; more reasoning-focused | 87.5% | #24 / 58 |
GPQAArtificial Analysis PhD-level science questions even experts struggle with | 91.1% | #25 / 88 |
MMMUvals.ai College-level multimodal reasoning across 30+ disciplines | 83% | #25 / 57 |
LiveCodeBenchvals.ai Contamination-free competitive programming (filtered by cutoff date) | 82.4% | #34 / 59 |