Skip to main content

Human ratings

Japanese (human ratings)

A category computed only from questions in Japanese.

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 1600Week
change
OverallInput $
/1M
Output $
/1M
ContextSupportsWeightsReleasedPrice and specs
1–15Claude Fable 5.1AnthropicRating 1551 ±37+41503rank 2–10$10$501MAnthropic Released 2026-⁠09 Week change +4 Price $10 / $50 Length 1M
1–27Claude Opus 5.5AnthropicRating 1532 ±43New1509rank 1–7$4$201MAnthropic Released 2026-⁠09 Price $4 / $20 Length 1M
1–24Claude Fable 5AnthropicRating 1521 ±25−21503rank 2–9$10$501MAnthropic Released 2026-⁠06 Week change −2 Price $10 / $50 Length 1M
1–30Gemini 3.7 FlashGoogleRating 1513 ±2901490rank 8–25$0.75$3.751.05MGoogle Released 2026-⁠08 Price $0.75 / $3.75 Length 1.05M
1–29Kimi K3⁠MoonshotRating 1511 ±25+61487rank 8–27$3$151.05MMoonshot Released 2026-⁠07 Week change +6 Price $3 / $15 Length 1.05M
1–27Claude Opus 5AnthropicRating 1509 ±20+51491rank 8–22$5$251MAnthropic Released 2026-⁠07 Week change +5 Price $5 / $25 Length 1M
1–30Gemini 3.8 FlashGoogleRating 1508 ±24+61496rank 4–15$0.75$3.751.05MGoogle Released 2026-⁠09 Week change +6 Price $0.75 / $3.75 Length 1.05M
1–30GPT-5.5OpenAIRating 1505 ±22+11482rank 12–36$5$301.05MOpenAI Released 2026-⁠04 Week change +1 Price $5 / $30 Length 1.05M
1–37Gemini 3 ProGoogleRating 1504 ±3001486rank 10–29——1.05MGoogle Released 2025-⁠11 Price — Length 1.05M
1–34Claude Opus 4.6AnthropicRating 1499 ±2101503rank 2–9$5$251MAnthropic Released 2026-⁠02 Price $5 / $25 Length 1M
1–38GPT-5.6 SolOpenAIRating 1497 ±25+11485rank 10–30$4$201.05MOpenAI Released 2026-⁠07 Week change +1 Price $4 / $20 Length 1.05M
2–33Gemini 3.1 Pro (preview)GoogleRating 1496 ±17−11487rank 10–26$2$121.05MGoogle Released 2026-⁠02 Week change −1 Price $2 / $12 Length 1.05M
1–43Claude Opus 4.7AnthropicRating 1490 ±2401501rank 2–10$5$251MAnthropic Released 2026-⁠04 Price $5 / $25 Length 1M
1–51Gemini 3 FlashGoogleRating 1489 ±3401473rank 23–49——1.05MGoogle Released 2025-⁠12 Price — Length 1.05M
1–68Qwen3.5 Max (preview)AlibabaRating 1484 ±4401465rank 36–60————Alibaba Released — Price — Length —
2–50GPT-5.4OpenAIRating 1480 ±25+11475rank 19–42$2.5$151.05MOpenAI Released 2026-⁠03 Week change +1 Price $2.5 / $15 Length 1.05M
2–50Gemini 3.5 FlashGoogleRating 1479 ±2401477rank 18–41$1.5$91.05MGoogle Released 2026-⁠05 Price $1.5 / $9 Length 1.05M
2–59Qwen3.8 MaxAlibabaRating 1478 ±28+31483rank 10–36$2$61MAlibaba Released 2026-⁠08 Week change +3 Price $2 / $6 Length 1M
1–70Grok 4.20 (beta1)xAIRating 1477 ±4001475rank 19–45————xAI Released — Price — Length —
2–57Gemini 3.6 FlashGoogleRating 1476 ±25−11483rank 10–35$0.75$3.751.05MGoogle Released 2026-⁠07 Week change −1 Price $0.75 / $3.75 Length 1.05M
2–65Muse Spark 1.3MetaRating 1476 ±33−71496rank 3–15$1.25$4.251.05MMeta Released 2026-⁠09 Week change −7 Price $1.25 / $4.25 Length 1.05M
3–60GPT-5.6 TerraOpenAIRating 1471 ±24−41467rank 28–53$2$121.05MOpenAI Released 2026-⁠07 Week change −4 Price $2 / $12 Length 1.05M
2–79Claude Sonnet 5.5AnthropicRating 1468 ±43New1478rank 14–44$2$101MAnthropic Released 2026-⁠09 Price $2 / $10 Length 1M
3–64Muse Spark 1.1MetaRating 1468 ±23−11490rank 8–23$1.25$4.251MMeta Released 2026-⁠07 Week change −1 Price $1.25 / $4.25 Length 1M
2–70GLM-5.3⁠Z.aiRating 1467 ±29+51481rank 11–38$1.4$4.41MZ.ai Released 2026-⁠08 Week change +5 Price $1.4 / $4.4 Length 1M
2–78GPT-5.5 InstantOpenAIRating 1464 ±3701473rank 20–50———OpenAI Released 2026-⁠05 Price — Length —
5–73GPT-5.1OpenAIRating 1461 ±2801456rank 49–72$1.25$10400KOpenAI Released 2025-⁠11 Price $1.25 / $10 Length 400K
9–69Claude Opus 4.8AnthropicRating 1461 ±21+11481rank 12–36$5$251MAnthropic Released 2026-⁠05 Week change +1 Price $5 / $25 Length 1M
9–73DeepSeek-V4 Pro⁠DeepSeekRating 1456 ±2401458rank 47–69$0.66$1.981MDeepSeek Released 2026-⁠04 Price $0.66 / $1.98 Length 1M
11–74GLM-5.2⁠Z.aiRating 1453 ±22−21475rank 19–43$1.4$4.41MZ.ai Released 2026-⁠06 Week change −2 Price $1.4 / $4.4 Length 1M
5–83DeepSeek-V4.1 Flash⁠DeepSeekRating 1453 ±36+71476rank 17–46——1MDeepSeek Released 2026-⁠09 Week change +7 Price — Length 1M
12–79GLM-5.3 Flash⁠Z.aiRating 1450 ±24+51476rank 19–43$0.15$0.51MZ.ai Released 2026-⁠08 Week change +5 Price $0.15 / $0.5 Length 1M
6–90GPT-5.2 ChatOpenAIRating 1449 ±3601476rank 19–42——128KOpenAI Released 2026-⁠02 Price — Length 128K
10–83Claude Opus 4.5AnthropicRating 1447 ±3101474rank 23–46$5$25200KAnthropic Released 2025-⁠11 Price $5 / $25 Length 200K
13–81Gemini 3.5 Flash-LiteGoogleRating 1445 ±26−11455rank 49–73$0.3$2.51.05MGoogle Released 2026-⁠07 Week change −1 Price $0.3 / $2.5 Length 1.05M
14–76Gemini 2.5 ProGoogleRating 1444 ±1501445rank 64–87$1.25$101MGoogle Released 2025-⁠06 Price $1.25 / $10 Length 1M
13–83Grok 4.5xAIRating 1444 ±2701466rank 33–55$2$6500KxAI Released 2026-⁠07 Price $2 / $6 Length 500K
9–95GPT-6 SolOpenAIRating 1443 ±37−21459rank 41–71$2$101.05MOpenAI Released 2026-⁠09 Week change −2 Price $2 / $10 Length 1.05M
13–81Claude Sonnet 5AnthropicRating 1443 ±23−21461rank 41–64$2$101MAnthropic Released 2026-⁠06 Week change −2 Price $2 / $10 Length 1M
13–87Kimi K2.6⁠MoonshotRating 1442 ±28−11461rank 41–65$0.95$4262.1KMoonshot Released 2026-⁠04 Week change −1 Price $0.95 / $4 Length 262.1K
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