context.vn
Menu

inference Bench

28 models evaluated

#ModelProviderTypeScore
4Claude Fable 5Anthropic · ClosedClaude Code · v2.1.175 · strict prompt8.74x
5Claude Opus 4.7Anthropic · ClosedClaude Code · v2.1.1758.53x
6GPT-6 AstraOpenAI · ClosedCodex CLI · strict prompt7.90x
7Claude Opus 4.8Anthropic · ClosedClaude Code · v2.1.1757.60x
9GPT-5.6 SolOpenAI · ClosedCodex CLI · strict prompt7.34x
11GLM-5.2Z.AI · Open weightClaude Code · v2.1.119 · strict prompt7.00x
12Grok 4.6xAI · ClosedGrok Build · strict prompt6.65x
13Claude Sonnet 5Anthropic · ClosedClaude Code · v2.1.119 · strict prompt6.43x
14Kimi K2.7 CodeMoonshot AI · Open weightOpenCode · strict prompt6.27x
15GPT-5.4OpenAI · ClosedCodex CLI6.16x
16Kimi K3Moonshot AI · ClosedOpenCode · strict prompt5.70x
17Claude Sonnet 4.6Anthropic · ClosedClaude Code5.56x
18GPT-5.3 CodexOpenAI · ClosedCodex CLI5.53x
19GPT-5.5OpenAI · ClosedCodex CLI5.45x
20GLM-5.3Z.AI · Open weightClaude Code · v2.1.119 · strict prompt4.98x
21Gemini 3.1 ProGoogle · ClosedOpenCode4.92x
22Kimi K2.6Moonshot AI · Open weightOpenCode4.51x
23GLM-5.3-FlashZ.AI · Open weightOpenCode · strict prompt4.49x
24Claude Opus 4.6Anthropic · ClosedClaude Code4.38x
25GPT-5.2OpenAI · ClosedCodex CLI4.28x
27Gemini 3.5 FlashGoogle · ClosedOpenCode4.16x
28Claude Opus 4.5Anthropic · ClosedClaude Code3.76x
29Grok 4.5xAI · ClosedGrok Build · strict prompt3.70x
30GPT-5.1-Codex-MaxOpenAI · ClosedCodex CLI3.59x
32GLM-5Z.AI · Open weightOpenCode3.22x
33Claude Sonnet 4.5Anthropic · ClosedClaude Code3.18x
35Claude Haiku 4.5Anthropic · ClosedClaude Code2.78x
39GPT-5.2-CodexOpenAI · ClosedCodex CLI1.98x