context.vn
Menu

charxiv

39 models evaluated

#ModelProviderTypeScore
1Qwen3.8 MaxAlibabaOpen weights93.5%
2Claude Mythos 5AnthropicProprietary93.5%
3Qwen3.8-Omni-FlashAlibabaProprietary91.4%
4Kimi K3Moonshot AI · Closed91.3%
5Claude Opus 4.7 (Adaptive)Anthropic · Closed91%
6Qwen3.8-Flash-NextAlibaba · Open weight90.6%
7Qwen3.8-27BAlibaba · Open weight90.2%
8Claude Opus 4.8Anthropic · Closed89.9%
9GLM-5.3-FlashZ.AI · Open weight89.4%
10Gemini 3.7 FlashGoogle · Closed88.7%
11Muse Spark 1.1Meta · Closed88.4%
12Claude Sonnet 5Anthropic · Closed88.3%
13Sakana Fugu-UltraSakana AI · Closed86.6%
14Muse SparkMeta · Closed86.4%
15Qwen3.7 PlusAlibaba · Closed85.9%
16Seed 2.1 ProByteDance · Closed85.4%
17Sakana FuguSakana AI · Closed85.1%
18Gemini 3.5 FlashGoogle · Closed84.2%
19GPT-5.4OpenAI · Closed82.8%
20Seed 2.1 TurboByteDance · Closed82.5%
21GPT-5.2OpenAI · Closed82.1%
22InklingThinking Machines Lab · Open weight82%
23Qwen3.6 PlusAlibaba · Closed81.5%
24Gemini 3 ProGoogle · Closed81.4%
25Inkling-SmallThinking Machines Lab · Open weight81.3%
26MiMo-V2.5Xiaomi · Closed81%
27Qwen3.5 397BAlibaba · Open weight80.8%
28Kimi K2.6Moonshot AI · Open weight80.4%
29Gemini 3.1 ProGoogle · Closed80.2%
30Muse Glimmer 30BMeta · Open weight78.8%
31Qwen3.6-27BAlibaba · Open weight78.4%
32Qwen3.6-35B-A3BAlibaba · Open weight78%
33Claude Sonnet 4.6Anthropic · Closed77.4%
34Qwen3.5-122B-A10BAlibaba · Open weight77.2%
35Nemotron 3 Nano Omni 30B A3BNVIDIA · Open weight76.3%
36Gemini 3.1 Flash-LiteGoogle · Closed73.2%
37Claude Opus 4.5Anthropic · Closed68.5%
38Grok 4.20xAI · Closed60.9%
39Command A+Cohere · Open weight52.7%