context.vn
Menu

erqa

13 models evaluated

#ModelProviderTypeScore
1Qwen3.8 MaxAlibabaOpen weights77.8%
2Qwen3.8-Flash-NextAlibabaOpen weights72.3%
3Seed 2.1 ProByteDanceProprietary72.0%
4Seed 2.1 TurboByteDance · Closed71.3%
5Qwen3.8-Omni-FlashAlibaba · Closed71.0%
6Qwen3.7 PlusAlibaba · Closed69.8%
7Gemini 3.1 ProGoogle · Closed69.4%
8Qwen3.8-27BAlibaba · Open weight65.5%
9GPT-5.4OpenAI · Closed65.4%
10Muse SparkMeta · Closed64.7%
11Qwen3.6-27BAlibaba · Open weight62.5%
12Grok 4.20xAI · Closed54.1%
13Claude Opus 4.6Anthropic · Closed51.6%