AI Models: Benchmarks and Specs
Every model we track, ranked by the Artificial Analysis Intelligence Index v5.0.1 as of Nov 8, 2026, a combined score from 9 tests that compares selected abilities, not overall usefulness. Higher is better. A dash means we have no verified number. Select a model for its scores, specs and news.
| Model | Made by | Index | Price per 1M (in / out) | Released | Weights | Download size |
|---|---|---|---|---|---|---|
| Gemini 4 Carbon | 60 | $4 / $20 | Oct 28, 2026 | Closed | - | |
| Claude Opus 5.5 | Anthropic | 59.1 | $4 / $20 | Sep 22, 2026 | Closed | - |
| GPT-6 Astra | OpenAI | 56.9 | $10 / $50 | Sep 3, 2026 | Closed | - |
| GPT-6.1 Sol | OpenAI | 54.6 | $2 / $10 | Sep 29, 2026 | Closed | - |
| Claude Sonnet 5.5 | Anthropic | 54.5 | $2 / $10 | Sep 28, 2026 | Closed | - |
| GPT-6.1 Terra | OpenAI | 51.3 | $1 / $5 | Oct 26, 2026 | Closed | - |
| Gemini 4 Argon | 50.4 | $4 / $20 | Sep 30, 2026 | Closed | - | |
| Muse Wonder Full | Meta | 50.1 | - | Oct 12, 2026 | Closed | - |
| Claude Fable 5.1 | Anthropic | 49.2 | $10 / $50 | Sep 1, 2026 | Closed | - |
| Kimi K3.1 Pro | Kimi | 46.5 | $2 / $10 | Oct 23, 2026 | Open | 1.56 TB |
| Muse Wonder | Meta | 43.6 | $4 / $20 | Oct 12, 2026 | Closed | - |
| Claude Haiku 5.5 | Anthropic | 36.5 | $0.1 / $0.5 | Oct 7, 2026 | Closed | - |
| Grok 4.7 | SpaceXAI | 35.5 | $2 / $6 | Sep 21, 2026 | Closed | - |
| Tencent Hy4 | Tencent | 34.6 | $0.834 / $2.501 | - | Closed | - |
| Qwen3.8 Max | Alibaba | 33.7 | $2 / $6 | Aug 3, 2026 | Closed | - |
| DeepSeek V4.1 Flash 1017 | DeepSeek | 32.6 | $0.3 / $1.2 | Oct 17, 2026 | Open | 510.3 GB |
| GLM-5.3 | Z AI | 31.7 | $1.4 / $4.4 | Aug 18, 2026 | Open | 755.6 GB |
| Gemini 3.8 Flash | 30.8 | $0.75 / $3.75 | Sep 2, 2026 | Closed | - | |
| Inkling 2 Small | Thinking Machines | 30.6 | $0.3 / $1 | - | Closed | - |
| MiMo-V2.6-Pro | Xiaomi | 29.9 | $0.435 / $0.87 | Sep 21, 2026 | Open | - |
| Ling 3.1 Flash 1019 | InclusionAI | 29.6 | $0.3 / $0.9 | - | Open | - |
| MiniMax-M3.1-Flash | MiniMax | 29.1 | $0.15 / $0.6 | Oct 19, 2026 | Open | - |
| Step 5 Preview | StepFun | 28.5 | $1 / $2.7 | - | Open | - |
| GPT-6 Luna | OpenAI | 27.9 | $0.1 / $0.5 | Sep 22, 2026 | Closed | - |
| GLM-5.3-Flash | Z AI | 27.8 | $0.15 / $0.5 | Aug 26, 2026 | Open | - |
| MiMo-V2.6-Flash | Xiaomi | 26.7 | $0.14 / $0.28 | Sep 21, 2026 | Open | - |
| Mistral Large 4 | Mistral | 26.1 | $0.7 / $2.1 | Oct 29, 2026 | Open | 1.06 TB |
| Muse Spark Open | Meta | 24.9 | $1.25 / $4.25 | Oct 15, 2026 | Open | - |
| DeepSeek V4 Pro 0813 | DeepSeek | 23.1 | $1.32 / $3.96 | Aug 13, 2026 | Open | 864.7 GB |
| Nanbeige4.3-33B | Nanbeige | 20.4 | - | Oct 25, 2026 | Open | - |
| Qwen3.8 27B | Alibaba | 20.1 | $0.5 / $3 | Aug 14, 2026 | Open | 55.6 GB |
| MiniMax-M3 | MiniMax | 18.9 | $0.3 / $1.2 | Jun 1, 2026 | Open | - |
| K2 Horizon 375B A23B | Institute of Foundation Models | 17.8 | - | Sep 3, 2026 | Open | - |
| Beam 1.0 | Reflection | 17.7 | $0.4 / $1.2 | Oct 16, 2026 | Open | - |
| Nemotron 3.5 Super VL | NVIDIA | 13.6 | $0.175 / $0.5 | Oct 15, 2026 | Open | - |
| Inkling Small | Thinking Machines | 12.9 | $0.3 / $1.2 | Jul 30, 2026 | Open | - |
| Inkling | Thinking Machines | 12.5 | $1 / $4.05 | Jul 15, 2026 | Open | - |
| Nemotron 3 Ultra 550B A55B | NVIDIA | 11.8 | $0.6 / $2.7 | - | Open | - |
| Gemini 3.5 Flash-Lite | 11.7 | $0.3 / $2.5 | Jul 21, 2026 | Closed | - | |
| K-EXAONE 2.0 | LG AI Research | 7.6 | - | Aug 12, 2026 | Open | - |
| Muse Glimmer | Meta | 6.3 | $0.3 / $1.2 | Aug 10, 2026 | Open | - |
| Command A+ | Cohere | 6.2 | - | May 20, 2026 | Open | - |
| Nemotron 3.5 Lightning | NVIDIA | 5.5 | $0.06 / $0.2 | Aug 11, 2026 | Open | - |
| Granite 4.2 8B | IBM | 5.1 | $0.06 / $0.25 | Aug 25, 2026 | Open | - |
| Granite 4.2 3B | IBM | 4.7 | - | Aug 25, 2026 | Open | - |
| Mistral Medium 3.5 | Mistral | 4.6 | $1.5 / $7.5 | Apr 29, 2026 | Open | - |
| Gemma 4 31B | 4.4 | - | Apr 2, 2026 | Open | 62.5 GB | |
| Mistral Small 4 | Mistral | 4.3 | $0.15 / $0.6 | Mar 16, 2026 | Open | - |
| North Mini Code | Cohere | 3.4 | - | Jun 9, 2026 | Open | - |
| NVIDIA Nemotron 3 Nano 4B | NVIDIA | 1.8 | - | Mar 16, 2026 | Open | - |
| Arete-27B | Nous Research | - | - | - | Open | 54.7 GB |
| DeepSeek V4 Flash | DeepSeek | - | - | - | Open | 159.6 GB |
| ERNIE 5.5 Flash Base | Baidu | - | - | - | Open | 288.4 GB |
| FLUX 3 | - | - | - | - | Closed | - |
| FLUX 3 Image | - | - | - | - | Closed | - |
| FLUX 3 Image Klein | Black Forest Labs | - | - | - | Open | 43.3 GB |
| FLUX 3 Max | - | - | - | - | Closed | - |
| GPT Image 2 | - | - | - | - | Closed | - |
| GPT Image 2.5 Flare | - | - | - | - | Closed | - |
| GPT Image 2.5 Sunburst | - | - | - | - | Closed | - |
| Kimi K3 | Moonshot AI | - | - | - | Open | 1.56 TB |
| MAI-Image-2.6 | - | - | - | - | Closed | - |
| MiMo-V2.6-Pro RL | Xiaomi | - | - | - | Open | 573.5 GB |
| Ming-3.0-tts 0.5b | inclusionAI | - | - | - | Open | 3 GB |
| MiniMax H3 | - | - | - | - | Open | - |
| Nano Banana 2.1 | - | - | - | - | Closed | - |
| Qwen-Image-2.1 | Alibaba | - | - | - | Open | 33.1 GB |
| Qwen3.8 2.4T-A95B | Alibaba | - | - | - | Open | 4.89 TB |
| Ripple-65B Preview | Ricursive Intelligence | - | - | - | Open | 129.6 GB |
| Seedance 2.5 | - | - | - | - | Closed | - |
| Utopai X | - | - | - | - | Closed | - |
| Wan 3.0 | - | - | - | - | Closed | - |
Filtering by price or size hides models we have no verified number for. Download size is not the memory needed to run a model.