Skip to content

Newest models

Most recent releases, with whatever independent scores exist so far.

Most recent releases, with whatever independent scores exist so far. Source: OpenRouter / Epoch AI. Variants (reasoning effort, batch) are folded into one row.

#ModelCapabilityReasoningCodingContext$/M
101Fugu UltraSakana AI———1M$11.25
102Nano Banana 2 (Gemini 3.1 Flash Image)Google———131K$1.13
103Nano Banana Pro (Gemini 3 Pro Image)Google———131K$4.50
104GLM 5.2Z.ai (Zhipu AI)151.891.943.81.05M$1.39
105Kimi K2.7 CodeMoonshot AI150.087.930.5262K$1.32
106Claude Fable 5Anthropic · +5 variants163.685.969.71M$20.00
107Nemotron 3 UltraNVIDIA146.285.4—262K$1.05
108Nemotron 3.5 Content SafetyNVIDIA———131K$0.20
109Qwen3.7 PlusAlibaba (Qwen)147.487.9—1M$0.56
110MiniMax M3MiniMax147.090.9—1.05M$0.53
111Claude Opus 4.8Anthropic · +1 variant158.391.059.01M$10.00
112Step 3.7 FlashStepFun———262K$0.44
113Grok Build 0.1xAI———256K$1.25
114Gemini 3.5 FlashGoogle · +1 variant154.692.837.41.05M$3.38
115Qwen3.7 MaxAlibaba (Qwen)153.790.9—1M$2.21
116Composer 2.5Anysphere—————
117Perceptron Mk1Perceptron———33K$0.49
118AI co-mathematicianGoogle—————
119Gemini 3.1 Flash LitebatchGoogle · +1 variant———1.05M$0.28
120GPT-5.5 InstantOpenAI142.582.5———
121GPT Chat LatestOpenAI———400K$11.25
122Grok 4.3xAI · +1 variant———1M$1.56
123Mistral Medium 3.5batchMistral AI · +1 variant———262K$1.50
124Laguna M.1Poolside—————
125Laguna XS.2Poolside—————
126Qwen 3.6 FlashAlibaba (Qwen)143.3————
127Qwen 3.6 Flash (2026-04-16)Alibaba (Qwen)—83.3———
128Qwen3.6 35B A3BAlibaba (Qwen)—84.8—262K$0.36
129Qwen3.6 FlashAlibaba (Qwen)———1M$0.42
130Qwen3.6 Max PreviewAlibaba (Qwen)———262K$2.31
131DeepSeek V4 Pro 0423DeepSeek149.1——1.05M$1.19
132DeepSeek V4 Flash 0423DeepSeek146.1——1.05M$0.17
133DeepSeek v4unknownDeepSeek—————
134DeepSeek v4 FlashmaxDeepSeek—————
135DeepSeek v4 Prounknown thinkingDeepSeek · +1 variant—73.2———
136GPT-5.5batchOpenAI · +6 variants———1.05M$5.63
137GPT-5.5 ProbatchOpenAI · +3 variants———1.05M$33.75
138Qwen3.6 27BAlibaba (Qwen)146.585.9—262K$1.04
139Hy3 previewTencent———262K$0.28
140MiMo-V2.5Xiaomi———1.05M$0.17
141MiMo-V2.5-ProXiaomi———1.05M$0.54
142GPT-5.4 Image 2OpenAI———272K$9.75
143Kimi K2.6Moonshot AI151.090.8—262K$1.34
144Qwen 3.6 Max (Preview)Alibaba (Qwen)149.387.4———
145Grok 4.3 BetaxAI149.188.8———
146Claude Opus 4.7Anthropic · +6 variants156.486.4—1M$10.00
147Qwen 3.6 35B-A3BAlibaba (Qwen)143.9————
148Muse SparkMeta152.189.8———
149GLM 5.1Z.ai (Zhipu AI)149.989.9—205K$2.15
150Claude Mythos Preview (Early)Anthropic—————
— means no published score from that source yet · click a model for every benchmark with its source
Best AI for coding →
Models ranked on DeepSWE
Best AI for reasoning →
Ranked on GPQA Diamond
Best AI for math →
Ranked on competition math
Best open-weight models →
Weights you can run yourself
Cheapest capable models →
Lowest blended API price
Best AI coding tools →
Apps & agents by popularity
Best AI image generators →
Apps & models
Best AI for research →
Answer engines & deep research