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
- Qwen3.5-0.8BAlibaba Group · 2 Mar 2026 · 262.1K context—in / 1M
- Qwen3.5-2BAlibaba Group · 2 Mar 2026 · 262.1K context—in / 1M
- Qwen3.5-4BAlibaba Group · 2 Mar 2026 · 262.1K context—in / 1M
- Qwen3.5-9BAlibaba Group · 2 Mar 2026 · 262.1K context—in / 1M
- Granite 4.0 3B VisionIBM · 3 Mar 2026 · 131.1K context—in / 1M
- Nemotron 3 Content SafetyNVIDIA · 6 Mar 2026 · 131.1K context—in / 1M
- Nemotron 3 Nano 4BNVIDIA · 7 Mar 2026 · 262.1K context—in / 1M
- Nemotron 3 Super 120B-A12BNVIDIA · 11 Mar 2026 · 1M context—in / 1M
- Reka Edge 2603Reka AI · 11 Mar 2026 · 16.4K context$0.10in / 1M
- Mistral Small 4Mistral AI · 16 Mar 2026 · 262.1K context$0.15in / 1M
- MiniMax-M2.7MiniMax · 18 Mar 2026 · 204.8K context$0.30in / 1M
- Voxtral TTSMistral AI · 23 Mar 2026 · — context—in / 1M
- Cohere TranscribeCohere · 24 Mar 2026 · — context—in / 1M
- Harrier OSS v1 0.6BMicrosoft · 30 Mar 2026 · — context—in / 1M
- Harrier OSS v1 270MMicrosoft · 30 Mar 2026 · — context—in / 1M
- Harrier OSS v1 27BMicrosoft · 30 Mar 2026 · — context—in / 1M
- Gemma 4 26B A4BGoogle DeepMind · 31 Mar 2026 · 262.1K context—in / 1M
- Gemma 4 31BGoogle DeepMind · 31 Mar 2026 · 262.1K context—in / 1M
- Gemma 4 E2BGoogle DeepMind · 31 Mar 2026 · 131.1K context—in / 1M
- Gemma 4 E4BGoogle DeepMind · 31 Mar 2026 · 131.1K context—in / 1M
- jina-embeddings-v5-omni (nano, small)Jina AI · 31 Mar 2026 · — context—in / 1M
- LFM2.5-350MLiquid AI · 31 Mar 2026 · 32.8K context—in / 1M
- HY-World 2.0Tencent · Apr 2026 · — context—in / 1M
- Ling-2.6-1TAnt Group · Apr 2026 · 262.1K context—in / 1M
- Ling-2.6-flashAnt Group · Apr 2026 · 131.1K context—in / 1M
- MiMo-V2.5-ASRXiaomi · Apr 2026 · — context—in / 1M
- MiniCPM-V-4.6ModelBest · Apr 2026 · 262.1K context—in / 1M
- Nemotron OCR v2NVIDIA · 1 Apr 2026 · — context—in / 1M
- SenseNova-U1-8B-MoTSenseTime · Apr 2026 · 262.1K context—in / 1M
- Trinity Large ThinkingArcee AI · 1 Apr 2026 · 262.1K context$0.25in / 1M
- Granite 4.1 30BIBM · 6 Apr 2026 · 131.1K context—in / 1M
- Granite 4.1 3BIBM · 6 Apr 2026 · 131.1K context—in / 1M
- Granite 4.1 8BIBM · 6 Apr 2026 · 131.1K context—in / 1M
- GLM-5.1Z.ai (Zhipu AI) · 7 Apr 2026 · 204.8K context$1.40in / 1M
- LFM2.5-VL-450MLiquid AI · 8 Apr 2026 · 32.8K context—in / 1M
- EXAONE-4.5-33BLG AI Research · 9 Apr 2026 · 262.1K context—in / 1M
- ERNIE-ImageBaidu · 15 Apr 2026 · — context—in / 1M
- Granite Guardian 4.1 8BIBM · 16 Apr 2026 · 131.1K context—in / 1M
- Granite Speech 4.1 2B (and 2B-plus, 2B-NAR)IBM · 16 Apr 2026 · — context—in / 1M
- Granite Vision 4.1 4BIBM · 16 Apr 2026 · 131.1K context—in / 1M
- Qwen3.6-35B-A3BAlibaba Group · 16 Apr 2026 · 262.1K context$0.38in / 1M
- Granite Embedding Multilingual R2 (97M, 311M)IBM · 20 Apr 2026 · — context—in / 1M
- Hy3 previewTencent · 20 Apr 2026 · 262.1K context—in / 1M
- Kimi K2.6Moonshot AI · 20 Apr 2026 · 262.1K context$0.95in / 1M
- MiMo-V2.5Xiaomi · 22 Apr 2026 · 1M context—in / 1M
- MiMo-V2.5-ProXiaomi · 22 Apr 2026 · 1M context—in / 1M
- Qwen3.6-27BAlibaba Group · 22 Apr 2026 · 262.1K context$0.60in / 1M
- Laguna XS.2Poolside · 23 Apr 2026 · 262.1K context—in / 1M
- DeepSeek-V4-FlashDeepSeek · 24 Apr 2026 · 1M context—in / 1M
- DeepSeek-V4-ProDeepSeek · 24 Apr 2026 · 1M context$1.32in / 1M