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
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
- Baichuan-M1-14B-InstructBaichuan Intelligence · Jan 2025 · 32.8K context—in / 1M
- Baichuan-Omni-1.5Baichuan Intelligence · Jan 2025 · 65.5K context—in / 1M
- Hunyuan-7B-InstructTencent · Jan 2025 · 262.1K context—in / 1M
- Hunyuan3D 2Tencent · Jan 2025 · — context—in / 1M
- KwaiCoder-23B-A4B-v1Kuaishou · Jan 2025 · 4.1K context—in / 1M
- Llama 3.1 Tulu 3 405BAllen Institute for AI (Ai2) · Jan 2025 · 131.1K context—in / 1M
- MiniCPM-o-2.6ModelBest · Jan 2025 · 32.8K context—in / 1M
- ReaderLM-v2Jina AI · Jan 2025 · 512K context—in / 1M
- SonarPerplexity · Jan 2025 · 128K context$1.00in / 1M
- Sonar ProPerplexity · Jan 2025 · 200K context$3.00in / 1M
- TinySwallow-1.5B-InstructSakana AI · Jan 2025 · 32.8K context—in / 1M
- UI-TARS-2B-SFTByteDance · Jan 2025 · 32.8K context—in / 1M
- UI-TARS-72B-DPOByteDance · Jan 2025 · 32.8K context—in / 1M
- UI-TARS-7B-DPOByteDance · Jan 2025 · 32.8K context—in / 1M
- DeepSeek-V3DeepSeek · 26 Dec 2024 · 131.1K context—in / 1M
- CogAgent-9B-20241220Z.ai (Zhipu AI) · 20 Dec 2024 · — context—in / 1M
- DeepSeek-VL2DeepSeek · 13 Dec 2024 · 4.1K context—in / 1M
- DeepSeek-VL2-SmallDeepSeek · 13 Dec 2024 · 4.1K context—in / 1M
- DeepSeek-VL2-TinyDeepSeek · 13 Dec 2024 · 4.1K context—in / 1M
- Phi-4Microsoft · 12 Dec 2024 · 16.4K context$0.13in / 1M
- EXAONE-3.5-2.4B-InstructLG AI Research · 9 Dec 2024 · 32.8K context—in / 1M
- EXAONE-3.5-32B-InstructLG AI Research · 9 Dec 2024 · 32.8K context—in / 1M
- EXAONE-3.5-7.8B-InstructLG AI Research · 9 Dec 2024 · 32.8K context—in / 1M
- Llama 3.3 70BMeta · 6 Dec 2024 · 131.1K context—in / 1M
- PaliGemma 2 10BGoogle DeepMind · 5 Dec 2024 · — context—in / 1M
- PaliGemma 2 28BGoogle DeepMind · 5 Dec 2024 · — context—in / 1M
- PaliGemma 2 3BGoogle DeepMind · 5 Dec 2024 · — context—in / 1M
- voyage-code-3Voyage AI · 4 Dec 2024 · 32K context$0.18in / 1M
- Amazon Nova CanvasAmazon · 3 Dec 2024 · — context—in / 1M
- Amazon Nova LiteAmazon · 3 Dec 2024 · 300K context$0.06in / 1M
- Amazon Nova MicroAmazon · 3 Dec 2024 · 128K context$0.04in / 1M
- Amazon Nova ProAmazon · 3 Dec 2024 · 300K context$0.80in / 1M
- Amazon Nova ReelAmazon · 3 Dec 2024 · — context—in / 1M
- Hermes 3 Llama 3.2 3BNous Research · 3 Dec 2024 · 131.1K context—in / 1M
- Arctic Embed 2.0 (M, L)Snowflake · Dec 2024 · — context—in / 1M
- Command R7BCohere · Dec 2024 · 128K context$0.04in / 1M
- CosyVoice2-0.5BAlibaba Group · Dec 2024 · — context—in / 1M
- Falcon3-10B-InstructTechnology Innovation Institute (TII) · Dec 2024 · 32.8K context—in / 1M
- Falcon3-1B-InstructTechnology Innovation Institute (TII) · Dec 2024 · 8.2K context—in / 1M
- Falcon3-3B-InstructTechnology Innovation Institute (TII) · Dec 2024 · 32.8K context—in / 1M
- Falcon3-7B-InstructTechnology Innovation Institute (TII) · Dec 2024 · 32.8K context—in / 1M
- Falcon3-Mamba-7B-InstructTechnology Innovation Institute (TII) · Dec 2024 · — context—in / 1M
- Granite 3.1 1B-A400M InstructIBM · Dec 2024 · 131.1K context—in / 1M
- Granite 3.1 2B InstructIBM · Dec 2024 · 131.1K context—in / 1M
- Granite 3.1 3B-A800M InstructIBM · Dec 2024 · 131.1K context—in / 1M
- Granite 3.1 8B InstructIBM · Dec 2024 · 131.1K context—in / 1M
- Granite Embedding (30M, 125M English; 107M, 278M multilingual)IBM · Dec 2024 · — context—in / 1M
- Granite Guardian 3.1 (2B, 8B)IBM · Dec 2024 · — context—in / 1M
- HunyuanVideoTencent · Dec 2024 · — context—in / 1M
- InternVL2.5-1BShanghai AI Laboratory · Dec 2024 · 32.8K context—in / 1M