context.vn

pp Bench

41 models evaluated

#ModelProviderTypeScore
1GPT-5.5OpenAIClosedgpt-5.5@xhigh
2GPT-5.4OpenAIClosedgpt-5.4@xhigh
3GPT-5.2OpenAIClosedgpt-5.2@xhigh
4Claude Opus 4.7claude-opus-4-7@thinkingAnthropicClosed
5Gemini 3.5 Flashgemini-3.5-flash@highGoogleClosed
8Claude Opus 4.6 (Adaptive)claude-opus-4-6@thinkingAnthropicClosed
9Gemini 3.1 Progemini-3.1-proGoogleClosed
10Claude Opus 4.6claude-opus-4-6AnthropicClosed
11Claude Sonnet 4.6claude-sonnet-4-6@thinkingAnthropicClosed
12GPT-5.2 Progpt-5.2-proOpenAIClosed
16Kimi K2.6kimi-k2.6Moonshot AIOpen
17Gemini 3 Progemini-3-pro@highGoogleClosed
22Qwen3.6 Plusqwen3.6-plusAlibabaClosed
23GPT-5.1gpt-5.1@mediumOpenAIClosed
24Claude Opus 4.5 Thinkingclaude-opus-4-5@thinkingAnthropicClosed
25Gemini 3 Flashgemini-3-flash@minimalGoogleClosed
27Grok 4.20grok-4.20-reasoningxAIClosed
28GPT-5 (high)gpt-5@mediumOpenAIClosed
29Kimi K2.5kimi-k2.5Moonshot AIOpen
30Grok 4.1 Fastgrok-4-1-fastxAIClosed
31Grok 4.1 Fast (Reasoning)grok-4-1-fast-reasoningxAIClosed
32DeepSeek V4 Prodeepseek-v4-proDeepSeekOpen
33Grok 4.3grok-4.3@xhighxAIClosed
34o3OpenAIClosed3.3%
35MiniMax M2.5minimax-m2.5MiniMaxClosed
36Claude Opus 4.5claude-opus-4-5-highAnthropicClosed
37Claude Sonnet 4.5claude-sonnet-4-5AnthropicClosed
39Claude Sonnet 4.5 Thinkingclaude-sonnet-4-5@thinkingAnthropicClosed
40DeepSeek V3.2deepseek-v3.2DeepSeekOpen
42Kimi K2kimi-k2-thinkingMoonshot AIClosed
43MiMo-V2-Promimo-v2-proXiaomiClosed
44o1OpenAIClosed0.7%
45MiniMax M2.7minimax-m2.7MiniMaxOpen
47GLM-5glm-5Z.AIOpen
48Gemini 2.5 Progemini-2.5-proGoogleClosed
52GPT-OSS 120Bgpt-oss-120bOpenAIOpen
56MiMo-V2-Flashmimo-v2-flashXiaomiOpen
57GLM-4.7glm-4.7Z.AIOpen
58Grok Code Fast 1grok-code-fast-1xAIClosed
60GPT-4.1gpt-4.1OpenAIClosed
61GPT-4ogpt-4oOpenAIClosed