AI models
Browse 855 AI models with benchmark scores and latent capability estimates.
| Model | Organization | Capability | Parameters |
|---|---|---|---|
| Claude Mythos Preview | Anthropic | 166.3 | — |
| GPT-5.6 Sol Pro | OpenAI | 164.9 | — |
| Claude Mythos 5 | Anthropic | 164.2 | — |
| Claude Fable 5 | Anthropic | 164.2 | — |
| Claude Opus 5 | Anthropic | 163.8 | — |
| GPT-5.5 Pro | OpenAI | 162.9 | — |
| GPT-5.6 Terra Pro | OpenAI | 162.8 | — |
| GPT-5.6 Sol | OpenAI | 162.6 | — |
| Gemini 3 Deep Think | Google DeepMind | 161.4 | — |
| GPT-5.6 Luna Pro | OpenAI | 161.3 | — |
| GPT-5.4 Pro | OpenAI | 161.2 | — |
| GPT-5.6 Terra | OpenAI | 160.9 | — |
| Kimi K3 | Moonshot AI | 160.4 | — |
| GPT-5.5 | OpenAI | 160.3 | — |
| Opus 4.8 | Anthropic | 160.2 | — |
| GPT-5.6 Luna | OpenAI | 159.0 | — |
| Grok 4.5 | xAI | 158.9 | — |
| DeepSeek-V4-Flash-0731 | DeepSeek | 158.6 | — |
| Sonnet 5 | Anthropic | 158.4 | — |
| Opus 4.7 | Anthropic | 158.4 | — |
| Muse Spark 1.1 | Meta | 158.0 | — |
| GPT-5.4 | OpenAI | 157.7 | — |
| Gemini 3.5 Flash | Google DeepMind | 156.8 | — |
| Opus 4.6 | Anthropic | 156.8 | — |
| GPT-5.3-Codex | OpenAI | 156.7 | — |
| GPT-5.2 Pro | OpenAI | 156.6 | — |
| GLM-5.2 | Zhipu AI (Z.ai) | 156.5 | 753.3B |
| Gemini 3.6 Flash | Google DeepMind | 156.2 | — |
| Gemini 3.1 Pro Preview | Google DeepMind | 155.1 | — |
| Laguna S 2.1 | Poolside | 155.1 | 117.6B |
| Gemini 2.5 Deep Think | Google DeepMind | 154.8 | — |
| Sonnet 4.6 | Anthropic | 154.6 | — |
| Muse Spark | Meta | 154.6 | — |
| Hy3 | Tencent | 154.5 | 298.8B |
| Motif-3-Beta | Motif Technologies | 154.4 | 314.8B |
| Composer 2.5 | Cursor | 154.4 | — |
| GPT-5.2 | OpenAI | 154.2 | — |
| Nex-N2-Pro | Nex AGI | 154.2 | 396.8B |
| Qwen3.7-Max | Alibaba | 154.1 | — |
| GPT-5.2-Codex | OpenAI | 153.8 | — |