Spark-v3.5-Max: benchmark results
Provider: Other.
Aggregate Rating 1515 ± 28, rank #2117 of 10916 rated models, from 86 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenCompass Language - Intention Recognition - English (CompassBench 2405) | 86 | Score (%) | 100 |
| OpenCompass Reasoning - Common Sense - English (CompassBench 2405) | 50.7 | Score (%) | 100 |
| OpenCompass LLM - Reasoning (CompassBench 2405) | 54.3 | Score (%) | 97.4 |
| OpenCompass LLM - Reasoning - Chinese (CompassBench 2405) | 62.3 | Score (%) | 97.4 |
| OpenCompass LLM - Reasoning - English (CompassBench 2405) | 46.3 | Score (%) | 97.4 |
| OpenCompass Code - MBPP - English (CompassBench 2405) | 79.4 | Score (%) | 97.3 |
| OpenCompass Reasoning - Common Sense - Chinese (CompassBench 2405) | 57.1 | Score (%) | 96.1 |
| OpenCompass Reasoning - Abductive - Chinese (CompassBench 2405) | 90.8 | Score (%) | 94.7 |
| OpenCompass Reasoning - Deductive - Chinese (CompassBench 2405) | 61.1 | Score (%) | 94.7 |
| OpenCompass Reasoning - Inductive - Chinese (CompassBench 2405) | 40.1 | Score (%) | 94.7 |
| OpenCompass Code - HumanEval - Chinese (CompassBench 2405) | 66.5 | Score (%) | 92.1 |
| OpenCompass Code - HumanEval+ - English (CompassBench 2405) | 68.3 | Score (%) | 92.1 |
Interactive version: theaggregate.ai/model?slug=spark-v3-5-max · How It Works · Data refreshed daily, snapshot 2026-11-08.