Skip to main content

Human ratings

Chinese (human ratings)

A category computed only from questions in Chinese.

How to read this table

  • Higher rows are rated higher. A range like “1–2” means the gap is within the margin of error.
  • The rating comes from people comparing two answers and picking the better one.
  • At a gap of 50, the higher model is picked about 57% of the time; 100 means 64%, 200 means 76%.
  • Prices are a guide per million tokens, reading then writing.
  • Length is how much text the model can read at once (tokens).

± range of the top model

RankModelDeveloperratingrating scale 1400 to 1700Week
change
OverallInput $
/1M
Output $
/1M
ContextSupportsWeightsReleasedPrice and specs
1–8Gemini 4 ArgonGoogleRating 1579 ±22−91517rank 1–3$2$101.05MGoogle Released 2026-⁠09 Week change −9 Price $2 / $10 Length 1.05M
1–14Claude Opus 5.5AnthropicRating 1570 ±20−41509rank 1–7$4$201MAnthropic Released 2026-⁠09 Week change −4 Price $4 / $20 Length 1M
1–13Claude Fable 5.1AnthropicRating 1568 ±18+11503rank 2–10$10$501MAnthropic Released 2026-⁠09 Week change +1 Price $10 / $50 Length 1M
1–18Claude Fable 5AnthropicRating 1555 ±1101503rank 2–9$10$501MAnthropic Released 2026-⁠06 Price $10 / $50 Length 1M
1–21Claude Opus 4.6AnthropicRating 1551 ±9+11503rank 2–9$5$251MAnthropic Released 2026-⁠02 Week change +1 Price $5 / $25 Length 1M
1–27Gemini 3.7 FlashGoogleRating 1546 ±13+31490rank 8–25$0.75$3.751.05MGoogle Released 2026-⁠08 Week change +3 Price $0.75 / $3.75 Length 1.05M
2–23Claude Opus 5AnthropicRating 1546 ±901491rank 8–22$5$251MAnthropic Released 2026-⁠07 Price $5 / $25 Length 1M
1–50Muse WonderMetaRating 1544 ±27New1509rank 1–8$4$201.05MMeta Released 2026-⁠10 Price $4 / $20 Length 1.05M
1–42Claude Sonnet 5.5AnthropicRating 1542 ±22−51478rank 14–44$2$101MAnthropic Released 2026-⁠09 Week change −5 Price $2 / $10 Length 1M
2–31Kimi K3⁠MoonshotRating 1542 ±1201487rank 8–27$3$151.05MMoonshot Released 2026-⁠07 Price $3 / $15 Length 1.05M
2–31GPT-5.6 SolOpenAIRating 1541 ±1101485rank 10–30$4$201.05MOpenAI Released 2026-⁠07 Price $4 / $20 Length 1.05M
4–36Gemini 3.8 FlashGoogleRating 1538 ±11+51496rank 4–15$0.75$3.751.05MGoogle Released 2026-⁠09 Week change +5 Price $0.75 / $3.75 Length 1.05M
2–39GLM-5.3⁠Z.aiRating 1538 ±14+41481rank 11–38$1.4$4.41MZ.ai Released 2026-⁠08 Week change +4 Price $1.4 / $4.4 Length 1M
3–39Qwen3.8 MaxAlibabaRating 1537 ±13+41483rank 10–36$2$61MAlibaba Released 2026-⁠08 Week change +4 Price $2 / $6 Length 1M
4–36Claude Opus 4.7AnthropicRating 1537 ±10−11501rank 2–10$5$251MAnthropic Released 2026-⁠04 Week change −1 Price $5 / $25 Length 1M
5–42GLM-5.3 Flash⁠Z.aiRating 1532 ±12+21476rank 19–43$0.15$0.51MZ.ai Released 2026-⁠08 Week change +2 Price $0.15 / $0.5 Length 1M
4–52Muse Spark 1.3MetaRating 1531 ±15+21496rank 3–15$1.25$4.251.05MMeta Released 2026-⁠09 Week change +2 Price $1.25 / $4.25 Length 1.05M
5–48Gemini 3.6 FlashGoogleRating 1530 ±12+11483rank 10–35$0.75$3.751.05MGoogle Released 2026-⁠07 Week change +1 Price $0.75 / $3.75 Length 1.05M
6–49Muse Spark 1.1MetaRating 1529 ±11+11490rank 8–23$1.25$4.251MMeta Released 2026-⁠07 Week change +1 Price $1.25 / $4.25 Length 1M
7–42Gemini 3.1 Pro (preview)GoogleRating 1528 ±7+11487rank 10–26$2$121.05MGoogle Released 2026-⁠02 Week change +1 Price $2 / $12 Length 1.05M
7–52Claude Opus 4.8AnthropicRating 1525 ±10−11481rank 12–36$5$251MAnthropic Released 2026-⁠05 Week change −1 Price $5 / $25 Length 1M
7–53GPT-5.5OpenAIRating 1525 ±10+11482rank 12–36$5$301.05MOpenAI Released 2026-⁠04 Week change +1 Price $5 / $30 Length 1.05M
4–67Muse SparkMetaRating 1525 ±2001489rank 8–27———Meta Released 2026-⁠04 Price — Length —
8–55GLM-5.2⁠Z.aiRating 1523 ±10+21475rank 19–43$1.4$4.41MZ.ai Released 2026-⁠06 Week change +2 Price $1.4 / $4.4 Length 1M
6–69DeepSeek-V4.1 Flash⁠DeepSeekRating 1522 ±1901476rank 17–46——1MDeepSeek Released 2026-⁠09 Price — Length 1M
8–62Gemini 3 ProGoogleRating 1521 ±1001486rank 10–29——1.05MGoogle Released 2025-⁠11 Price — Length 1.05M
2–100Qwen3.7 Max (preview)AlibabaRating 1520 ±35−21474rank 15–53————Alibaba Released — Week change −2 Price — Length —
10–66Gemini 3.5 FlashGoogleRating 1518 ±11+11477rank 18–41$1.5$91.05MGoogle Released 2026-⁠05 Week change +1 Price $1.5 / $9 Length 1.05M
12–66GPT-5.6 TerraOpenAIRating 1517 ±1001467rank 28–53$2$121.05MOpenAI Released 2026-⁠07 Price $2 / $12 Length 1.05M
10–67Gemini 3 FlashGoogleRating 1517 ±1201473rank 23–49——1.05MGoogle Released 2025-⁠12 Price — Length 1.05M
8–73Qwen3.5 Max (preview)AlibabaRating 1517 ±1501465rank 36–60————Alibaba Released — Price — Length —
10–69Kimi K2.6⁠MoonshotRating 1516 ±1301461rank 41–65$0.95$4262.1KMoonshot Released 2026-⁠04 Price $0.95 / $4 Length 262.1K
10–71GLM-5⁠Z.aiRating 1516 ±1301457rank 47–70$1$3.2204.8KZ.ai Released 2026-⁠02 Price $1 / $3.2 Length 204.8K
7–85GPT-6.1 SolOpenAIRating 1514 ±22−91480rank 10–41$2$101.05MOpenAI Released 2026-⁠09 Week change −9 Price $2 / $10 Length 1.05M
14–67MiMo-V2.5 Pro⁠XiaomiRating 1513 ±9−11466rank 34–53$0.435$0.871.05MXiaomi Released 2026-⁠04 Week change −1 Price $0.435 / $0.87 Length 1.05M
14–70GLM-5.1⁠Z.aiRating 1513 ±901465rank 36–53$1.4$4.4200KZ.ai Released 2026-⁠04 Price $1.4 / $4.4 Length 200K
8–80GPT-6 AstraOpenAIRating 1512 ±18−21476rank 17–44$10$501.05MOpenAI Released 2026-⁠09 Week change −2 Price $10 / $50 Length 1.05M
5–108MiMo-V2.6 Pro⁠XiaomiRating 1511 ±33+21480rank 10–44$0.435$0.871.05MXiaomi Released 2026-⁠09 Week change +2 Price $0.435 / $0.87 Length 1.05M
12–79Grok 4.20 (beta1)xAIRating 1510 ±1501475rank 19–45————xAI Released — Price — Length —
17–73Claude Sonnet 4.6AnthropicRating 1509 ±901472rank 24–49$3$151MAnthropic Released 2026-⁠02 Price $3 / $15 Length 1M
How to read this page
  • These ratings exclude the effect of response length and formatting. Differences where the ± ranges overlap are within the margin of error, so about the same.
  • In the Supports column the icons are, from left: can use tools / can read images / can answer in a fixed format (JSON); faded means not supported or unknown.
  • Open-weights models have their contents (the weights) published, so you can also run them on your own computer or server. Models without the open-weights mark are normally used through the developer's own services (apps or API); for some models the weights status is unknown.
  • Names such as ChatGPT next to a model are the consumer services its developer offers. Check on the service itself whether that model is available there.

Data: Arena, Epoch AI, Swallow LLM team (CC BY 4.0), Models.dev (MIT), updated 2026-⁠10-⁠24, data sources