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 (via OpenRouter) — at a fraction of the price. Compare any two head-to-head, or scan the field below.
Last updated September 28, 2026 · Pricing September 28, 2026 · Benchmarks 2026-09-23
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, context & open weights. Claude Fable 5.1 leads on intelligence & modality.
| DeepSeek V4 Pro | Claude Fable 5.1 | |
|---|---|---|
| Intelligence (AA) | 30.4 | 53.4 |
| Blended $/1M | $0.979 | $20 |
| Value (intel/$) | 31.1 | 2.7 |
| Context | 1049K | 1000K |
| Modality | text | text, image, file |
| 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. GPT-6 Luna leads on value.
| Model▼ | Intelligence▼ | $/1M▼ | Value▼ | Context▼ | Modality | Open |
|---|---|---|---|---|---|---|
| Claude Opus 5.5US | 57.6 | $8 | 7.2 | 1M | TIAVF | · |
| Claude Fable 5.1US | 53.4 | $20 | 2.7 | 1M | TIAVF | · |
| GPT-6 SolUS | 47.5 | $4 | 11.9 | 1.1M | TIAVF | · |
| MiMo V2.6 ProCN | 46.3 | $0.544 | 85.1 | 1.1M | TIAVF | ● |
| GLM-5.3CN | 44.8 | $2.15 | 20.8 | 1.3M | TIAVF | · |
| Kimi K3CN | 43.6 | $6 | 7.3 | 1M | TIAVF | ● |
| GPT-5.6 TerraUS | 42.1 | $4.5 | 9.4 | 1.1M | TIAVF | · |
| Gemini 3.8 FlashUS | 40.9 | $1.5 | 27.3 | 1M | TIAVF | · |
| Qwen3.6 PlusCN | 40.5 | $0.731 | 55.4 | 1M | TIAVF | ● |
| DeepSeek V4.1 FlashCN | 39.5 | $0.525 | 75.2 | 1M | TIAVF | ● |
| GPT-6 LunaUS | 37.3 | $0.2 | 186.5 | 1.1M | TIAVF | · |
| Step 3.7 FlashCN | 30.9 | $0.438 | 70.5 | 262K | TIAVF | ● |
| DeepSeek V4 ProCN | 30.4 | $0.979 | 31.1 | 1M | TIAVF | ● |
| Gemini 3.1 ProUS | 29.7 | $4.5 | 6.6 | 1M | TIAVF | · |
| MiniMax M3CN | 29.2 | $0.525 | 55.6 | 1M | TIAVF | ● |
| Kimi K2.6CN | 27 | $1.34 | 20.1 | 262K | TIAVF | ● |
| Grok 4.3US | 24.9 | $1.562 | 15.9 | 1M | TIAVF | · |
| Mistral Medium 3.5EU | 14.2 | $3 | 4.7 | 262K | TIAVF | · |
| Llama 4 MaverickUS | 9.3 | $0.304 | 30.6 | 1M | TIAVF | ● |
| Hunyuan A13BCN | — | $0.247 | — | 131K | TIAVF | ● |
Blended $/1M tokens at a 3:1 input:output weighting. Intelligence = Artificial Analysis Index (blends coding, math, reasoning, agentic benchmarks), as republished by OpenRouter. Pricing is OpenRouter listed rates; native API pricing may differ. Intelligence as of 2026-09-23; pricing via OpenRouter, 2026-09-28. Benchmark configs vary by model, so treat the ability axis as directional. We refresh as new readings land.