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
- MiniMax Hailuo 2.3MiniMax · 28 Oct 2025 · — context—in / 1M
- LFM2-VL-3BLiquid AI · 22 Oct 2025 · 32.8K context—in / 1M
- Nemotron OCR v1NVIDIA · 21 Oct 2025 · — context—in / 1M
- Qwen3-VL-2B-InstructAlibaba Group · 21 Oct 2025 · 262.1K context—in / 1M
- Qwen3-VL-32B-InstructAlibaba Group · 21 Oct 2025 · 262.1K context$0.16in / 1M
- Llama Nemotron Embed 1B v2NVIDIA · 16 Oct 2025 · 131.1K context—in / 1M
- Llama Nemotron Rerank 1B v2NVIDIA · 16 Oct 2025 · — context—in / 1M
- PaddleOCR-VLBaidu · 16 Oct 2025 · — context—in / 1M
- Qwen3-VL-4B-InstructAlibaba Group · 15 Oct 2025 · 262.1K context—in / 1M
- Qwen3-VL-8B-InstructAlibaba Group · 15 Oct 2025 · 262.1K context$0.18in / 1M
- MAI-Image-1Microsoft · 13 Oct 2025 · — context—in / 1M
- Granite 4.0 1B (Nano)IBM · 7 Oct 2025 · 131.1K context—in / 1M
- Granite 4.0 350M (Nano)IBM · 7 Oct 2025 · 32.8K context—in / 1M
- Granite 4.0 H-1B (Nano)IBM · 7 Oct 2025 · 131.1K context—in / 1M
- Granite 4.0 H-350M (Nano)IBM · 7 Oct 2025 · 32.8K context—in / 1M
- LFM2-8B-A1BLiquid AI · 7 Oct 2025 · 32.8K context—in / 1M
- Llama-Embed-Nemotron 8BNVIDIA · 7 Oct 2025 · 131.1K context—in / 1M
- GPT Audio miniOpenAI · 6 Oct 2025 · 128K context$0.60in / 1M
- GPT Image 1 MiniOpenAI · 6 Oct 2025 · — context$2.00in / 1M
- GPT-Realtime miniOpenAI · 6 Oct 2025 · 32K context$0.60in / 1M
- Qwen3-VL-30B-A3B-InstructAlibaba Group · 3 Oct 2025 · 262.1K context$0.20in / 1M
- Deepgram Flux (English, Multilingual)Deepgram · Oct 2025 · — context—in / 1M
- DeepSeek-OCRDeepSeek · Oct 2025 · — context—in / 1M
- Granite 4.0 H-Micro (3B)IBM · Oct 2025 · 131.1K context—in / 1M
- Granite 4.0 H-Small (32B-A9B)IBM · Oct 2025 · 131.1K context—in / 1M
- Granite 4.0 H-Tiny (7B-A1B)IBM · Oct 2025 · 131.1K context—in / 1M
- Granite 4.0 Micro (3B)IBM · Oct 2025 · 131.1K context—in / 1M
- KAT-Dev-72B-ExpKuaishou · Oct 2025 · 131.1K context—in / 1M
- Ling-1TAnt Group · Oct 2025 · 32.8K context—in / 1M
- LongCat-Flash-OmniMeituan · Oct 2025 · 131.1K context—in / 1M
- LongCat-VideoMeituan · Oct 2025 · — context—in / 1M
- olmOCR 2 7BAllen Institute for AI (Ai2) · Oct 2025 · — context—in / 1M
- Omni-Embed-Nemotron 3BNVIDIA · 30 Sep 2025 · 32.8K context—in / 1M
- Wan2.5 Image PreviewAlibaba Group · 24 Sep 2025 · — context—in / 1M
- Qwen-Image-PlusAlibaba Group · 23 Sep 2025 · — context—in / 1M
- Qwen3-VL-235B-A22B-InstructAlibaba Group · 23 Sep 2025 · 262.1K context$0.40in / 1M
- Wan2.5-PreviewAlibaba Group · 23 Sep 2025 · — context—in / 1M
- LFM2-2.6BLiquid AI · 22 Sep 2025 · 32.8K context—in / 1M
- Qwen3-Omni-30B-A3B-CaptionerAlibaba Group · 22 Sep 2025 · — context$3.81in / 1M
- Qwen3-Omni-30B-A3B-InstructAlibaba Group · 22 Sep 2025 · — context—in / 1M
- jina-reranker-v3Jina AI · 18 Sep 2025 · — context—in / 1M
- Qwen3-TTS-FlashAlibaba Group · 16 Sep 2025 · — context—in / 1M
- Qwen3-Omni-Flash-RealtimeAlibaba Group · 15 Sep 2025 · — context—in / 1M
- VaultGemma 1BGoogle DeepMind · 13 Sep 2025 · — context—in / 1M
- Qwen3-Next-80B-A3B-InstructAlibaba Group · 11 Sep 2025 · 262.1K context$0.15in / 1M
- Qwen3-ASR-FlashAlibaba Group · 8 Sep 2025 · — context—in / 1M
- Palmyra mini (and mini-thinking a/b)Writer · 5 Sep 2025 · 131.1K context—in / 1M
- EmbeddingGemma 300MGoogle DeepMind · 4 Sep 2025 · 2K context—in / 1M
- Granite-Docling 258MIBM · Sep 2025 · — context—in / 1M
- Hunyuan-MT-7BTencent · Sep 2025 · 32.8K context—in / 1M