context.vn
Menu

ifeval

30 models evaluated

#ModelProviderTypeScore
4Qwen3.7 PlusAlibaba · ClosedIFEval metric view not recorded94.6%
5Qwen3.7 MaxAlibaba · ClosedIFEval metric view not recorded94.3%
6Qwen3.6 PlusAlibaba · ClosedIFEval metric view not recorded94.3%
7Kimi K2.5Moonshot AI · Open weightIFEval metric view not recorded93.9%
8dots3-note PreviewDots Studio · Open weightIFEval metric view not recorded93.9%
9o3-miniOpenAI · ClosedIFEval metric view not recorded93.9%
10Qwen3.5-122B-A10BAlibaba · Open weightIFEval metric view not recorded93.4%
11GLM-5Z.AI · Open weightIFEval metric view not recorded92.6%
12Qwen3.5 397BAlibaba · Open weightIFEval metric view not recorded92.6%
13K-EXAONE 2.0LG AI Research · Open weightIFEval metric view not recorded92.4%
14o1OpenAI · ClosedIFEval metric view not recorded92.2%
15Qwen3.5-35B-A3BAlibaba · Open weightIFEval metric view not recorded91.9%
16LFM2.5-8B-A1BLiquidAI · Open weightIFEval metric view not recorded91.8%
17Ternary Bonsai 2 27BPrism ML · Open weightIFEval metric view not recorded91.3%
18Claude Opus 4.5Anthropic · ClosedIFEval metric view not recorded90.9%
19GPT-4.1 miniOpenAI · ClosedIFEval metric view not recorded88.5%
20GPT-4.1OpenAI · ClosedIFEval metric view not recorded87.4%
21MiniCPM5-2BOpenBMB · Open weightIFEval metric view not recorded86.7%
22DeepSeek V3DeepSeek · Open weightIFEval metric view not recorded86.1%
23ZAYA1-8BZyphra · Open weightIFEval metric view not recorded85.6%
24GPT-4.1 nanoOpenAI · ClosedIFEval metric view not recorded83.2%
25LFM2.5-VL-3BLiquidAI · Open weightIFEval metric view not recorded82.3%
26Kanana-2 3B InstructKakao · Open weightIFEval metric view not recorded81.0%
27Celeris-1Celeris · ClosedIFEval metric view not recorded80.8%
28MiniCPM5-1BOpenBMB · Open weightIFEval metric view not recorded80.4%
29Kanana-2 1.3B InstructKakao · Open weightIFEval metric view not recorded77.6%
30Mellum2-12B-A2.5B-ThinkingJetBrains · Open weightIFEval metric view not recorded76.5%
31Mellum2-12B-A2.5B-InstructJetBrains · Open weightIFEval metric view not recorded75.8%
32LFM2.5-230MLiquidAI · Open weightIFEval metric view not recorded71.7%
33LFM2.5-VL-450MLiquidAI · Open weightIFEval metric view not recorded61.2%