Flagship ranking · 13 models
Overall LLM Leaderboard
A weighted composite ranking across seven dimensions — intelligence (30%), coding (20%), reasoning (15%), Chinese (10%), long context (8%), multimodal (7%) and value (10%). Click any model for the full breakdown.
Composite scores are edited estimates from public sources, not official results. See how we calculate them. Data as of 2026-11-20.
| # | Model | Overall | Intelligence | Coding | Reasoning | Chinese | Context | Price (in/out) |
|---|---|---|---|---|---|---|---|---|
| 1 | Anthropic · US | 93.3 | 98 | 99 | 97 | 88 | 1M | $4 / $20 |
| 2 | OpenAI · US | 90.1 | 95 | 91 | 96 | 86 | 1.1M | $10 / $50 |
| 3 | Moonshot AI · CN | 89.8 | 91 | 93 | 90 | 92 | 1M | $2 / $10 |
| 4 | Google · US | 89.7 | 92 | 86 | 88 | 90 | 1M | $2 / $10 |
| 5 | OpenAI · US | 89.3 | 90 | 88 | 89 | 85 | 1.1M | $2 / $10 |
| 6 | Anthropic · US | 88.9 | 89 | 92 | 87 | 85 | 1M | $2 / $10 |
| 7 | Alibaba Cloud · CN | 88.8 | 88 | 86 | 87 | 98 | 1M | $2 / $6 |
| 8 | Z.ai (Zhipu) · CN | 84.5 | 84 | 89 | 83 | 91 | 200K | $0.60 / $2.20 |
| 9 | xAI · US | 84.3 | 86 | 87 | 84 | 78 | 500K | $2 / $6 |
| 10 | DeepSeek · CN | 83.6 | 82 | 88 | 80 | 88 | 1M | $0.15 / $0.60 |
| 11 | ByteDance · CN | 82.7 | 81 | 78 | 80 | 95 | 256K | $0.30 / $1.20 |
| 12 | Mistral AI · EU | 80.5 | 80 | 80 | 79 | 76 | 1M | $0.70 / $2.10 |
| 13 | Meta · US | 78.5 | 77 | 76 | 75 | 74 | 1M | $0.20 / $0.60 |
Price shown as USD per 1M input / output tokens. Context is the maximum window.