Four specialized agents debate before answering, 65% hallucination reduction
| Benchmark | Score | Rank |
|---|---|---|
Arena Elo Human preference ranking via blind comparisons | 1491 | #4 / 41 |
ARC-AGIARC Prize Novel reasoning tasks requiring fluid intelligence | 65.1% | #5 / 21 |
SWE-bench Real-world GitHub issue resolution | 75% | #14 / 38 |
GPQA PhD-level science questions even experts struggle with | 88% | #16 / 54 |
TerminalArtificial Analysis Agentic terminal coding tasks requiring multi-step execution | 37.9% | #19 / 37 |
MMMUArtificial Analysis College-level multimodal reasoning across 30+ disciplines | 74.6% | #23 / 33 |
MMLU Tests knowledge across 57 subjects from STEM to humanities | 86.6% | #37 / 53 |