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
301nvidia-nemotron-nano-9b-v2—————
302Mistral Medium 3.1Mistral AI · +1 variant———131K$0.80
303GLM 4.5VZ.ai (Zhipu AI)———66K$0.90
304GPT-5OpenAI · +5 variants150.086.2—400K$3.44
305GPT-5 MiniOpenAI · +5 variants145.575.0—400K$0.69
306GPT-5 NanoOpenAI · +5 variants139.469.4—400K$0.14
307qwen3-4b-instruct-2507—45.8———
308Claude Opus 4.1Anthropic · +2 variants144.177.3—200K$30.00
309gpt-oss-120bOpenAI · +2 variants139.975.8—131K$0.070
310gpt-oss-20bOpenAI · +1 variant137.860.8—131K$0.036
311GLM-4.5 ThinkingZ.ai (Zhipu AI)—————
312Codestral 2508Mistral AI · +1 variant———256K$0.45
313Gemini 2.5 Deep ThinkGoogle—————
314Qwen3 Coder 30B A3B InstructAlibaba (Qwen)———262K$0.12
315Qwen3-30B-A3B-Thinking (Jul 2025)Alibaba (Qwen)139.670.1———
316Qwen3-30B-A3B-Instruct (Jul 2025)Alibaba (Qwen)137.455.6———
317Qwen3 30B A3B Instruct 2507Alibaba (Qwen)———262K$0.084
318chutes/GLM-4.5-FP8—————
319Qwen3-235B-A22B-Thinking (Jul 2025)Alibaba (Qwen)143.980.1———
320Qwen3-235B-A22B-Instruct (Jul 2025)Alibaba (Qwen)138.9————
321GLM 4.5Z.ai (Zhipu AI)———131K$1.00
322GLM 4.5 AirZ.ai (Zhipu AI)———131K$0.31
323Qwen3 235B A22B Thinking 2507Alibaba (Qwen)———131K$0.75
324Qwen3 Coder 480B A35BAlibaba (Qwen)———262K$0.47
325Gemini 2.5 Flash LiteGoogle · +1 variant———1.05M$0.17
326UI-TARS 7BByteDance———128K$0.13
327Qwen3 235B A22B Instruct 2507Alibaba (Qwen)———262K$0.15
328Kimi K2 (Jul 2025)Moonshot AI140.1————
329Kimi K2 InstructMoonshot AI—————
330Kimi K2 0711Moonshot AI———131K$1.00
331Grok 4 Heavy (web app)xAI—————
332Grok 4xAI146.587.0———
333UncensoredVenice———128K$0.38
334Hunyuan A13B InstructTencent———131K$0.25
335Morph V3 FastMorph———82K$0.90
336Morph V3 LargeMorph———262K$1.15
337ERNIE 4.5 VL 424B A47BBaidu———123K$0.63
338Grok-3 minixAI140.376.3———
339Mistral Small 3.2Mistral AI131.749.1———
340Mistral Small 3.2 24BMistral AI———256K$0.13
341Gemini 2.5 Flash (Jun 2025)Google140.8————
342Gemini 2.5 Flash-Lite (Jun 2025)Google133.9————
343Gemini 2.5 FlashGoogle · +1 variant———1.05M$0.85
344Gemini 2.5 ProGoogle · +1 variant———1.05M$3.44
345gemini-2.5-flash-lite-preview-06-17 (Default thinking length)Google—————
346MiniMax M1MiniMax———1M$0.85
347MiniMax-M1-80kMiniMax—————
348o3 ProOpenAI147.4——200K$35.00
349Magistral Small 1.0Mistral AI133.256.1———
350Magistral Medium 1.1Mistral AI—————
— 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