360Zhinao2-O1.5: benchmark results
Provider: Other.
Unified ELO 1630 ± 37, rank #371 of 1605 rated models, from 67 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SuperCLUE General (May 2025) - Math Reasoning | 62.86 | Score | 97.4 |
| OpenCompass LLM - Instruction Following - Chinese (CompassBench 2504) | 73.2 | Score (%) | 92.6 |
| SuperCLUE General (May 2025) - Science Reasoning | 50.52 | Score | 89.7 |
| OpenCompass LLM - Instruction Following (CompassBench 2504) | 67.4 | Score (%) | 88.9 |
| OpenCompass Math - Competition - English (CompassBench 2504) | 75 | Score (%) | 88.9 |
| OpenCompass LLM - Language - Chinese (CompassBench 2504) | 85.6 | Score (%) | 85.2 |
| OpenCompass Language - Creation - Chinese (CompassBench 2504) | 87.2 | Score (%) | 85.2 |
| SuperCLUE General (May 2025) - Code Generation | 87.14 | Score | 84.6 |
| OpenCompass LLM - Math - English (CompassBench 2504) | 65.5 | Score (%) | 83.3 |
| OpenCompass LLM - Instruction Following - English (CompassBench 2504) | 61.6 | Score (%) | 77.8 |
| OpenCompass Language - Dialogue - Chinese (CompassBench 2504) | 93.7 | Score (%) | 77.8 |
| OpenCompass Math - Reasoning Computation - English (CompassBench 2504) | 69.4 | Score (%) | 77.8 |
Interactive version: theaggregate.ai/model?slug=360zhinao2-o1-5 · How It Works · Data refreshed daily, snapshot 2026-09-26.