How China's models stack up
China's flagship models land within a few points of the best proprietary systems on Artificial Analysis Intelligence Index — at a fraction of the price. Compare any two head-to-head, or scan the field below.
Head-to-head
The fastest way to see how a Chinese model compares to a Western one. Pick two and read the one-line verdict.
Pick any two models to compare. The radar is the shape at a glance — each spoke is scaled so the outer edge = best in class, so a bigger shape is stronger overall. The table has the exact numbers; bold = the winner on that row.
DeepSeek V4 Pro leads on price, value & open weights. GPT-5.5 leads on intelligence, context & modality.
| DeepSeek V4 Pro | GPT-5.5 | |
|---|---|---|
| Intelligence (AA) | 52 | 60.2 |
| Blended $/1M | $0.544 | $11.25 |
| Value (intel/$) | 95.6 | 5.4 |
| Context | 1049K | 1050K |
| Modality | text | file, image, text |
| Open weights | Yes | No |
Price vs. ability
Bottom-right is the sweet spot: smarter and cheaper.
All models
Click any column to sort — highest intelligence, lowest cost, best value (intelligence per dollar), longest context. DeepSeek V4 Flash leads on value.
| Model▼ | Intelligence▼ | $/1M▼ | Value▼ | Context▼ | Modality | Open |
|---|---|---|---|---|---|---|
| GPT-5.5US | 60.2 | $11.25 | 5.4 | 1.1M | TIAVF | · |
| Claude Opus 4.7US | 57.3 | $10 | 5.7 | 1M | TIAVF | · |
| Gemini 3.1 ProUS | 57.2 | $4.5 | 12.7 | 1M | TIAVF | · |
| Gemini 3.5 FlashUS | 55 | $3.375 | 16.3 | 1M | TIAVF | · |
| Kimi K2.6CN | 54 | $1.42 | 38 | 262K | TIAVF | ● |
| MiMo V2.5 ProCN | 54 | $0.544 | 99.3 | 1M | TIAVF | ● |
| Grok 4.3US | 53 | $1.563 | 33.9 | 1M | TIAVF | · |
| DeepSeek V4 ProCN | 52 | $0.544 | 95.6 | 1M | TIAVF | ● |
| Qwen3.6 PlusCN | 50 | $0.731 | 68.4 | 1M | TIAVF | ● |
| GLM-5.1CN | 49.8 | $1.505 | 33.1 | 203K | TIAVF | ● |
| MiniMax M2.7CN | 49.6 | $0.509 | 97.4 | 205K | TIAVF | ● |
| DeepSeek V4 FlashCN | 47 | $0.125 | 376 | 1M | TIAVF | ● |
| Step 3.5 FlashCN | — | $0.143 | — | 262K | TIAVF | ● |
| Hunyuan A13BCN | — | $0.247 | — | 131K | TIAVF | ● |
| Llama 4 MaverickUS | — | $0.262 | — | 1M | TIAVF | ● |
| Mistral Medium 3.5EU | — | $3 | — | 262K | TIAVF | · |
Blended $/1M tokens at a 3:1 input:output weighting. Intelligence = Artificial Analysis Index (blends coding, math, reasoning, agentic benchmarks). Pricing is OpenRouter listed rates; native API pricing may differ. Intelligence as of 2026-05; pricing via OpenRouter, 2026-05-29. Benchmark configs vary by model, so treat the ability axis as directional. We refresh as new readings land.