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· Embedding
Context
Input price
Weights
Reasoning
| Model | Maker | Kind | Released | Context | Input $/1M | Output $/1M |
|---|---|---|---|---|---|---|
| text-embedding-3-largeOpenAI text embeddings | OpenAI | Embedding | 25 Jan 2024 | 8.2K | $0.13 | — |
| text-embedding-3-smallOpenAI text embeddings | OpenAI | Embedding | 25 Jan 2024 | 8.2K | $0.02 | — |
| text-embedding-ada-002OpenAI text embeddings · Legacy | OpenAI | Embedding | 15 Dec 2022 | 8.2K | $0.10 | — |
| CLIP ViT-L/14@336pxCLIP · Open weights | OpenAI | Embedding | Apr 2022 | — | — | — |
| CLIP ViT-L/14 and RN50x64CLIP · Legacy · Open weights | OpenAI | Embedding | Jan 2022 | — | — | — |
| CLIP ViT-B/16 and RN50x16CLIP · Legacy · Open weights | OpenAI | Embedding | Jul 2021 | — | — | — |
| CLIP (RN50, ViT-B/32 and RN101, RN50x4)CLIP · Legacy · Open weights | OpenAI | Embedding | Jan 2021 | — | — | — |
- text-embedding-3-largeOpenAI · 25 Jan 2024 · 8.2K context$0.13in / 1M
- text-embedding-3-smallOpenAI · 25 Jan 2024 · 8.2K context$0.02in / 1M
- text-embedding-ada-002OpenAI · 15 Dec 2022 · 8.2K context$0.10in / 1M
- CLIP ViT-L/14@336pxOpenAI · Apr 2022 · — context—in / 1M
- CLIP ViT-L/14 and RN50x64OpenAI · Jan 2022 · — context—in / 1M
- CLIP ViT-B/16 and RN50x16OpenAI · Jul 2021 · — context—in / 1M
- CLIP (RN50, ViT-B/32 and RN101, RN50x4)OpenAI · Jan 2021 · — context—in / 1M