Updated daily at 05:00 UTC
Models
AI models
1521 current models, newest first. Each links to its benchmark results, with who ran them.
Best by specialty
Independent and third-party results only · method category-2026-09-29.1
Not ranked yet
Too few independent or third-party results to rank:
Scientific reasoning, Mathematics, Long context, OCR & documents, Law, Medicine & health, Finance, Multilingual, Instruction following, Writing, Speech & audio.
All current models
Best for
- Knowledge & reasoning
- Scientific reasoning
- Mathematics
- Coding & software engineering
- Agentic tool use
- Computer & browser use
- Professional knowledge work
- Long context
- Vision & multimodal understanding
- OCR & documents
- Law
- Medicine & health
- Finance
- Multilingual
- Factuality & hallucination
- Instruction following
- Writing
- Speech & audio
- Human preference
Kind
Context
Input price
Weights
Reasoning· Not reasoning
- Hunyuan-MT-Chimera-7BTencent · Sep 2025 · 32.8K context—in / 1M
- HunyuanImage-2.1Tencent · Sep 2025 · — context—in / 1M
- HunyuanImage-3.0Tencent · Sep 2025 · — context—in / 1M
- KAT-Dev-32BKuaishou · Sep 2025 · 131.1K context—in / 1M
- Kling 2.5 TurboKuaishou · Sep 2025 · — context—in / 1M
- Ling-flash-2.0Ant Group · Sep 2025 · 32.8K context—in / 1M
- Ling-mini-2.0Ant Group · Sep 2025 · 32.8K context—in / 1M
- LongCat-Flash-ChatMeituan · 1 Sep 2025 · 131.1K context—in / 1M
- MiMo-Audio-7B-InstructXiaomi · Sep 2025 · — context—in / 1M
- Seedream 4.0ByteDance · Sep 2025 · — context—in / 1M
- Command A TranslateCohere · 28 Aug 2025 · 8K context$2.50in / 1M
- GPT AudioOpenAI · 28 Aug 2025 · 128K context$2.50in / 1M
- GPT-RealtimeOpenAI · 28 Aug 2025 · 32K context$4.00in / 1M
- LFM2-Audio-1.5BLiquid AI · 28 Aug 2025 · — context—in / 1M
- MAI-1-previewMicrosoft · 28 Aug 2025 · — context—in / 1M
- MAI-Voice-1Microsoft · 28 Aug 2025 · — context—in / 1M
- Gemini 2.5 Flash Image (Nano Banana)Google DeepMind · 26 Aug 2025 · 65.5K context$0.30in / 1M
- jina-code-embeddings (0.5B, 1.5B)Jina AI · 26 Aug 2025 · — context—in / 1M
- FastVLM 0.5BApple · 25 Aug 2025 · — context—in / 1M
- FastVLM 1.5BApple · 25 Aug 2025 · — context—in / 1M
- FastVLM 7BApple · 25 Aug 2025 · — context—in / 1M
- Fun-ASRAlibaba Group · 25 Aug 2025 · — context—in / 1M
- text-embedding-v4Alibaba Group · 25 Aug 2025 · — context—in / 1M
- VibeVoice 1.5BMicrosoft · 25 Aug 2025 · — context—in / 1M
- Llama 3.1 Nemotron Safety Guard 8B v3NVIDIA · 20 Aug 2025 · 131.1K context—in / 1M
- MobileCLIP2Apple · 19 Aug 2025 · — context—in / 1M
- Qwen-Image-EditAlibaba Group · 18 Aug 2025 · — context—in / 1M
- Gemma 3 270MGoogle DeepMind · 14 Aug 2025 · 32.8K context—in / 1M
- LFM2-VL-1.6BLiquid AI · 12 Aug 2025 · 32.8K context—in / 1M
- LFM2-VL-450MLiquid AI · 12 Aug 2025 · 32.8K context—in / 1M
- rerank-2.5 (and rerank-2.5-lite)Voyage AI · 11 Aug 2025 · 32K context$0.05in / 1M
- Qwen3-4B-Instruct-2507Alibaba Group · 6 Aug 2025 · 262.1K context—in / 1M
- Speech 2.5MiniMax · 6 Aug 2025 · — context—in / 1M
- Canary 1B v2NVIDIA · 4 Aug 2025 · — context—in / 1M
- Granite Embedding Reranker English R2IBM · 4 Aug 2025 · — context—in / 1M
- Parakeet TDT 0.6B v3NVIDIA · 4 Aug 2025 · — context—in / 1M
- Qwen-ImageAlibaba Group · 4 Aug 2025 · — context—in / 1M
- NextStep-1StepFun · Aug 2025 · — context—in / 1M
- OLMoASRAllen Institute for AI (Ai2) · Aug 2025 · — context—in / 1M
- Step-Audio 2 miniStepFun · Aug 2025 · — context—in / 1M
- Command A VisionCohere · 31 Jul 2025 · 128K context$2.50in / 1M
- FLUX.1 Krea [dev]Black Forest Labs · 31 Jul 2025 · — context—in / 1M
- Qwen3-Coder-30B-A3B-InstructAlibaba Group · 31 Jul 2025 · 262.1K context$0.45in / 1M
- Codestral 25.08Mistral AI · 30 Jul 2025 · 131.1K context$0.30in / 1M
- Qwen3-30B-A3B-Instruct-2507Alibaba Group · 30 Jul 2025 · 262.1K context$0.20in / 1M
- AFM-4.5BArcee AI · 29 Jul 2025 · — context—in / 1M
- Arctic-TILT v1.3Snowflake · 28 Jul 2025 · — context—in / 1M
- Hunyuan TurboS Vision VideoTencent · 28 Jul 2025 · 24.6K context—in / 1M
- Qwen3-Coder-FlashAlibaba Group · 28 Jul 2025 · 1M context$0.30in / 1M
- Wan2.2Alibaba Group · 28 Jul 2025 · — context—in / 1M