通义千问2.5: benchmark results

Provider: Other.

Aggregate Rating 1556 ± 41, rank #1613 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
SuperCLUE General (June 2024) - Liberal Arts76Score93.8
SuperCLUE-Code3 (May 2024) - Overall63.32Difficulty-Weighted Score78.6
SuperCLUE-Code3 - Overall80.3Score70.6
SuperCLUE General (June 2024) - Science72Score59.4
SuperCLUE General (June 2024) - Overall71Score54.7
SuperCLUE General (June 2024) - Hard63Score50

Interactive version: theaggregate.ai/model?slug=2-5 · How It Works · Data refreshed daily, snapshot 2026-11-08.