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· Open weights
Reasoning
- Step3-VL-10BStepFun · Jan 2026 · 65.5K context—in / 1M
- LFM2.5-VL-1.6BLiquid AI · 5 Jan 2026 · 32.8K context—in / 1M
- LFM2.5-1.2B-InstructLiquid AI · 6 Jan 2026 · 32.8K context—in / 1M
- Qwen3-VL-EmbeddingAlibaba Group · 8 Jan 2026 · — context—in / 1M
- Qwen3-VL-RerankerAlibaba Group · 8 Jan 2026 · — context—in / 1M
- Falcon-H1-Tiny (90M to 0.6B)Technology Innovation Institute (TII) · 12 Jan 2026 · — context—in / 1M
- MedGemma 1.5 4BGoogle DeepMind · 13 Jan 2026 · — context—in / 1M
- GLM-ImageZ.ai (Zhipu AI) · 14 Jan 2026 · — context—in / 1M
- TranslateGemma 12BGoogle DeepMind · 15 Jan 2026 · — context—in / 1M
- TranslateGemma 27BGoogle DeepMind · 15 Jan 2026 · — context—in / 1M
- TranslateGemma 4BGoogle DeepMind · 15 Jan 2026 · — context—in / 1M
- voyage-4-nanoVoyage AI · 15 Jan 2026 · 32K context—in / 1M
- GLM-4.7-FlashZ.ai (Zhipu AI) · 19 Jan 2026 · 204.8K context$0.00in / 1M
- LFM2.5-1.2B-ThinkingLiquid AI · 20 Jan 2026 · 32.8K context—in / 1M
- VibeVoice-ASRMicrosoft · 21 Jan 2026 · — context—in / 1M
- jina-embeddings-v5-text (nano, small)Jina AI · 22 Jan 2026 · — context—in / 1M
- Qwen3-TTS (open)Alibaba Group · 22 Jan 2026 · — context—in / 1M
- DeepSeek-OCR 2DeepSeek · 27 Jan 2026 · — context—in / 1M
- Kimi K2.5Moonshot AI · 27 Jan 2026 · 262.1K context—in / 1M
- SERA 32BAllen Institute for AI (Ai2) · 27 Jan 2026 · 41K context—in / 1M
- Trinity Large (Preview)Arcee AI · 27 Jan 2026 · — context—in / 1M
- Olmo Hybrid 7BAllen Institute for AI (Ai2) · 28 Jan 2026 · 65.5K context—in / 1M
- PaddleOCR-VL-1.5Baidu · 29 Jan 2026 · — context—in / 1M
- Qwen3-ASR (open)Alibaba Group · 29 Jan 2026 · — context—in / 1M
- Intern-S1-ProShanghai AI Laboratory · Feb 2026 · 262.1K context—in / 1M
- Ling-2.5-1TAnt Group · Feb 2026 · 131.1K context—in / 1M
- Ming-flash-omni-2.0Ant Group · Feb 2026 · 32.8K context—in / 1M
- MiniCPM-o-4.5ModelBest · Feb 2026 · 41K context—in / 1M
- MiniCPM-SALAModelBest · Feb 2026 · 524.3K context—in / 1M
- MiniMax-M2.5MiniMax · Feb 2026 · 204.8K context$0.30in / 1M
- Qwen3-Coder-NextAlibaba Group · Feb 2026 · 262.1K context$0.30in / 1M
- Ring-2.5-1TAnt Group · Feb 2026 · 131.1K context—in / 1M
- GLM-OCRZ.ai (Zhipu AI) · 3 Feb 2026 · — context—in / 1M
- Voxtral Mini Transcribe RealtimeMistral AI · 4 Feb 2026 · — context—in / 1M
- LongCat-Flash-LiteMeituan · 5 Feb 2026 · 262.1K context—in / 1M
- GLM-5Z.ai (Zhipu AI) · 12 Feb 2026 · 204.8K context$1.00in / 1M
- Tiny Aya (Global, Earth, Fire, Water)Cohere · 13 Feb 2026 · 8K context—in / 1M
- Qwen3.5-397B-A17BAlibaba Group · 16 Feb 2026 · 262.1K context$0.60in / 1M
- Nemotron Parse v1.2NVIDIA · 18 Feb 2026 · — context—in / 1M
- Sarvam-105BSarvam AI · 18 Feb 2026 · 131.1K context—in / 1M
- Sarvam-30BSarvam AI · 18 Feb 2026 · 131.1K context—in / 1M
- Falcon-OCRTechnology Innovation Institute (TII) · 22 Feb 2026 · — context—in / 1M
- LFM2-24B-A2BLiquid AI · 24 Feb 2026 · 32.8K context—in / 1M
- Qwen3.5-122B-A10BAlibaba Group · 24 Feb 2026 · 262.1K context$0.40in / 1M
- Qwen3.5-27BAlibaba Group · 24 Feb 2026 · 262.1K context$0.30in / 1M
- Qwen3.5-35B-A3BAlibaba Group · 24 Feb 2026 · 262.1K context$0.25in / 1M
- Granite 4.0 1B SpeechIBM · 27 Feb 2026 · — context—in / 1M
- PLaMo 2.1 2B VLPreferred Networks · Mar 2026 · — context—in / 1M
- PLaMo 2.1 8B VLPreferred Networks · Mar 2026 · — context—in / 1M
- Qianfan-OCRBaidu · Mar 2026 · — context—in / 1M