Rankings
Ranked by Agentic Index, combining multi-step tool use and agent tasks.
- 86
- ranked
- Index
- measure
Labs in the top 86
Google10
Anthropic9
Alibaba9
OpenAI8
Mistral8- Other labs42
86 ranked
| Rank | Model | Index | Providers | Context | Input | Output | Released |
|---|---|---|---|---|---|---|---|
| 1 | Claude Fable 5.1Anthropic | 57.9 | 37 | 1M | $10.00 | $50.00 | Sep 1, 2026 |
| 2 | Claude Opus 5Anthropic | 56.5 | 42 | 1M | $5.00 | $25.00 | Jul 24, 2026 |
| 3 | Qwen3.8 Max 0902Alibaba | 56.0 | 9 | 1M | $1.71 | $5.14 | Sep 2, 2026 |
| 4 |  Muse Spark 1.3Meta | 55.5 | 18 | 1.05M | $1.25 | $4.25 | Sep 2, 2026 |
| 5 |  GLM-5.3Zhipu AI · Open weights | 53.1 | 91 | 1M | $1.20 | $4.18 | Aug 14, 2026 |
| 6 |  Grok 4.6xAI | 53.0 | 33 | 500K | $2.00 | $6.00 | Aug 12, 2026 |
| 7 | GPT-6 AstraOpenAI | 51.0 | 37 | 1.05M | $10.00 | $50.00 | Sep 4, 2026 |
| 8 | GLM-5.3-FlashZhipu AI · Open weights | 50.9 | 84 | 1M | $0.30 | $1.05 | Sep 18, 2026 |
| 9 | Claude Fable 5Anthropic | 50.7 | 46 | 1M | $10.00 | $50.00 | Jun 7, 2026 |
| 10 | GPT-5.6 SolOpenAI | 50.2 | 49 | 1.05M | $4.00 | $20.00 | Jul 9, 2026 |
| 11 | Qwen3.8 2.4T A95BAlibaba · Open weights | 50.1 | 23 | 262K | $2.50 | $6.25 | Aug 12, 2026 |
| 12 |  Kimi K3Moonshot AI · Open weights | 50.0 | 83 | 1.05M | $3.00 | $15.00 | Jul 16, 2026 |
| 13 |  DeepSeek V4 Flash Vision ExpDeepSeek · Open weights | 47.5 | 14 | 1M | $0.15 | $0.60 | Aug 21, 2026 |
| 14 | Qwen3.8 27BAlibaba · Open weights | 45.8 | 50 | 262K | $0.40 | $3.00 | Aug 14, 2026 |
| 15 | Claude Sonnet 5Anthropic | 43.6 | 44 | 1M | $2.00 | $10.00 | Jun 29, 2026 |
| 16 | Muse Spark 1.2Meta | 43.2 | 18 | 1.05M | $1.25 | $4.25 | Aug 5, 2026 |
| 16 | GPT-5.6 TerraOpenAI | 43.2 | 45 | 1.05M | $2.00 | $12.00 | Jul 9, 2026 |
| 18 | GPT-5.6 LunaOpenAI | 42.1 | 48 | 1.05M | $0.20 | $1.20 | Jul 9, 2026 |
| 19 | Claude Opus 4.8Anthropic | 41.9 | 50 | 1M | $5.00 | $25.00 | May 28, 2026 |
| 20 | DeepSeek V4 Pro 0813DeepSeek · Open weights | 41.3 | 43 | 1.05M | $0.66 | $1.98 | Aug 13, 2026 |
| 21 | Grok 4.5xAI | 41.2 | 27 | 500K | $2.00 | $6.00 | Jul 8, 2026 |
| 22 | DeepSeek V4 Flash 0731DeepSeek · Open weights | 41.0 | 54 | 1.05M | $0.13 | $0.26 | Jul 31, 2026 |
| 23 | Gemini 3.8 FlashGoogle | 40.2 | 32 | 1.05M | $0.75 | $3.75 | Sep 2, 2026 |
| 24 | Claude Opus 4.7Anthropic | 38.6 | 48 | 1M | $5.00 | $25.00 | Apr 14, 2026 |
| 25 | GLM-5.2Zhipu AI · Open weights | 38.4 | 87 | 1M | $1.20 | $4.18 | Jun 13, 2026 |
| 26 | GPT-5.5OpenAI | 36.4 | 51 | 1.05M | $5.00 | $30.00 | Apr 23, 2026 |
| 27 | Claude Sonnet 4.6Anthropic | 31.8 | 52 | 1M | $3.00 | $15.00 | Feb 17, 2026 |
| 28 |  MiniMax-M3MiniMax · Open weights | 29.5 | 55 | 1M | $0.30 | $1.20 | Jun 1, 2026 |
| 29 | Gemini 3.6 FlashGoogle | 29.0 | 31 | 1.05M | $0.75 | $3.75 | Jul 21, 2026 |
| 30 |  Ling 3.0 Flash VLinclusionAI · Open weights | 28.7 | 6 | 131K | $0.06 | $0.18 | Sep 10, 2026 |
| 31 | DeepSeek V4 FlashDeepSeek · Open weights | 26.3 | 53 | 1M | $0.45 | $1.35 | Apr 24, 2026 |
| 31 | DeepSeek V4 ProDeepSeek · Open weights | 26.3 | 62 | 1.05M | $1.00 | $2.50 | Apr 24, 2026 |
| 33 | Muse Spark 1.1Meta | 25.8 | 14 | 1.05M | $1.25 | $4.25 | Apr 8, 2026 |
| 34 |  Hy3 previewTencent · Open weights | 24.1 | 4 | 262K | $0.18 | $0.60 | Apr 20, 2026 |
| 35 | GLM-5.1Zhipu AI · Open weights | 23.9 | 50 | 200K | $0.90 | $3.59 | Apr 7, 2026 |
| 36 |  Inkling SmallThinking Machines · Open weights | 23.5 | 11 | 262K | $0.30 | $1.20 | Jul 30, 2026 |
| 37 | InklingThinking Machines · Open weights | 22.5 | 20 | 262K | $1.00 | $4.05 | Jul 15, 2026 |
| 37 | Qwen3.7 MaxAlibaba | 22.5 | 31 | 1M | $2.50 | $7.50 | May 21, 2026 |
| 39 |  MiMo-V2.5-ProXiaomi · Open weights | 21.3 | 20 | 1.05M | $0.43 | $0.87 | Apr 22, 2026 |
| 40 | Kimi K2.7 CodeMoonshot AI · Open weights | 21.0 | 56 | 262K | $1.90 | $8.00 | Jun 12, 2026 |