SpaceXAI frontier model focused on coding, agentic tasks, and professional knowledge work.
| Benchmark | Score | Rank |
|---|---|---|
GPQAArtificial Analysis PhD-level science questions even experts struggle with | 93.1% | #6 / 73 |
LiveCodeBenchvals.ai Contamination-free competitive programming (filtered by cutoff date) | 87.4% | #7 / 48 |
MMLU-Provals.ai Harder 10-option successor to MMLU; more reasoning-focused | 89.2% | #8 / 45 |
hleArtificial Analysis | 40.3% | #8 / 61 |
MMMUvals.ai College-level multimodal reasoning across 30+ disciplines | 61.8% | #41 / 46 |