context.vn
Menu

gert Labs

54 models evaluated

#ModelProviderTypeScore
1Claude Opus 4.8AnthropicProprietary72.97%
2GPT-5.5OpenAIProprietary72.93%
3Claude Opus 4.7AnthropicProprietary65.59%
4GPT-5.4OpenAI · Closed64.89%
5Qwen3.7 MaxAlibaba · Closed64.27%
6Claude Opus 4.5Anthropic · Closed64.23%
7Gemini 3 ProGoogle · Closed63.23%
8Claude Sonnet 4.6Anthropic · Closed62.92%
9MiMo-V2.5-ProXiaomi · Closed62.70%
10Gemini 3.5 FlashGoogle · Closed61.85%
11Claude Opus 4.6Anthropic · Closed61.85%
12GLM-5.1Z.AI · Open weight60.11%
13GPT-5.3 CodexOpenAI · Closed57.47%
14Gemini 3.1 ProGoogle · Closed56.87%
15Kimi K2.6Moonshot AI · Open weight56.82%
16Gemini 3 FlashGoogle · Closed56.63%
17Qwen3.6-27BAlibaba · Open weight54.84%
19GPT-5.2-CodexOpenAI · Closed51.79%
20Step 3.7 FlashStepFun · Open weight51.57%
21GLM-5Z.AI · Open weight50.99%
22Qwen3.6 PlusAlibaba · Closed50.60%
23GPT-5.1-CodexOpenAI · Closed49.68%
24Grok Build 0.1xAI · Closed49.15%
25Claude Sonnet 4.5Anthropic · Closed48.51%
26Grok 4.1 FastxAI · Closed47.32%
27MiMo-V2.5Xiaomi · Closed46.89%
28Qwen3.5 397BAlibaba · Open weight46.76%
29GPT-5.2OpenAI · Closed46.54%
30Kimi K2.5Moonshot AI · Open weight45.88%
31Grok 4.3xAI · Closed43.86%
32Qwen3 MaxAlibaba · Closed43.74%
33Qwen3.6-35B-A3BAlibaba · Open weight42.65%
34Grok 4xAI · Closed42.34%
35Gemini 2.5 ProGoogle · Closed42.01%
36GPT-5.1OpenAI · Closed41.24%
37MiniMax M2.7MiniMax · Open weight40.40%
38GLM-4.7Z.AI · Open weight39.95%
39Claude 4 SonnetAnthropic · Closed39.66%
40Qwen3.5-27BAlibaba · Open weight39.41%
41MiniMax M2.5MiniMax · Closed39.11%
42Mistral Medium 3.5 128BMistral · Open weight39.10%
43Gemini 3.1 Flash-LiteGoogle · Closed38.46%
44Grok 4.20xAI · Closed38.36%
45Hy3 PreviewTencent · Open weight36.91%
46MiMo-V2-ProXiaomi · Closed36.68%
47Gemma 4 31BGoogle · Open weight35.26%
48Kimi K2.5 (Reasoning)Moonshot AI · Closed32.58%
49Trinity-Large-ThinkingArcee AI · Open weight32.55%
50GLM-5V-TurboZ.AI · Closed30.76%
51GPT-OSS 120BOpenAI · Open weight29.61%
52DeepSeek V3.2DeepSeek · Open weight29.57%
53Qwen3.5-35B-A3BAlibaba · Open weight28.96%
54GPT-4.1OpenAI · Closed25.65%
55Nemotron 3 Super 120B A12BNVIDIA · Open weight25.34%