abab6.5: benchmark results
Provider: MiniMax. Access: API.
Aggregate Rating 1511 ± 19, rank #2180 of 10916 rated models, from 127 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenCompass LLM - Reasoning - English (CompassBench 2405) | 47.2 | Score (%) | 100 |
| OpenCompass Reasoning - Inductive - Chinese (CompassBench 2405) | 59.6 | Score (%) | 100 |
| OpenCompass Reasoning - Inductive - English (CompassBench 2405) | 90.5 | Score (%) | 100 |
| OpenCompass Math - College - Chinese (CompassBench 2405) | 44.7 | Score (%) | 94.7 |
| OpenCompass Reasoning - Abductive - English (CompassBench 2405) | 87.5 | Score (%) | 92.1 |
| OpenCompass Math - Middle - English (CompassBench 2404) | 57 | Score (%) | 92 |
| OpenCompass Math - High - Chinese (CompassBench 2404) | 28.4 | Score (%) | 90 |
| OpenCompass Subjective - Math (CompassBench 2404) | 46 | Score (%) | 90 |
| OpenCompass LLM - Reasoning (CompassBench 2405) | 50.1 | Score (%) | 89.5 |
| OpenCompass Language - Chinese Semantic Understanding - Chinese (CompassBench 2405) | 73.7 | Score (%) | 89.5 |
| OpenCompass LLM - Average (CompassBench 2404) | 57.8 | Score (%) | 89 |
| OpenCompass Code - HumanEval+ - English (CompassBench 2405) | 67.7 | Score (%) | 88.2 |
Interactive version: theaggregate.ai/model?slug=abab6-5 · How It Works · Data refreshed daily, snapshot 2026-11-08.