Skip to main content

Human ratings

Longer query (human ratings)

A category computed only from long questions.

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 1450 to 1550Week
change
OverallInput $
/1M
Output $
/1M
ContextSupportsWeightsReleasedPrice and specs
1–4Gemini 4 ArgonGoogleRating 1535 ±10−91517rank 1–3$2$101.05MGoogle Released 2026-⁠09 Week change −9 Price $2 / $10 Length 1.05M
1–7Claude Opus 5.5AnthropicRating 1524 ±10+31509rank 1–7$4$201MAnthropic Released 2026-⁠09 Week change +3 Price $4 / $20 Length 1M
1–6Claude Fable 5AnthropicRating 1522 ±6+11503rank 2–9$10$501MAnthropic Released 2026-⁠06 Week change +1 Price $10 / $50 Length 1M
1–6Claude Opus 4.6AnthropicRating 1521 ±5−11503rank 2–9$5$251MAnthropic Released 2026-⁠02 Week change −1 Price $5 / $25 Length 1M
2–9Claude Opus 4.7AnthropicRating 1515 ±501501rank 2–10$5$251MAnthropic Released 2026-⁠04 Price $5 / $25 Length 1M
2–18Claude Fable 5.1AnthropicRating 1510 ±8+21503rank 2–10$10$501MAnthropic Released 2026-⁠09 Week change +2 Price $10 / $50 Length 1M
4–17Gemini 3.8 FlashGoogleRating 1510 ±601496rank 4–15$0.75$3.751.05MGoogle Released 2026-⁠09 Price $0.75 / $3.75 Length 1.05M
6–21Claude Opus 4.8AnthropicRating 1503 ±501481rank 12–36$5$251MAnthropic Released 2026-⁠05 Price $5 / $25 Length 1M
6–25Claude Opus 5AnthropicRating 1503 ±601491rank 8–22$5$251MAnthropic Released 2026-⁠07 Price $5 / $25 Length 1M
6–25Kimi K3⁠MoonshotRating 1503 ±6−11487rank 8–27$3$151.05MMoonshot Released 2026-⁠07 Week change −1 Price $3 / $15 Length 1.05M
5–32Muse WonderMetaRating 1502 ±12−31509rank 1–8$4$201.05MMeta Released 2026-⁠10 Week change −3 Price $4 / $20 Length 1.05M
6–25Gemini 3.7 FlashGoogleRating 1501 ±6+31490rank 8–25$0.75$3.751.05MGoogle Released 2026-⁠08 Week change +3 Price $0.75 / $3.75 Length 1.05M
5–33Claude Sonnet 5.5AnthropicRating 1499 ±10−11478rank 14–44$2$101MAnthropic Released 2026-⁠09 Week change −1 Price $2 / $10 Length 1M
7–25Gemini 3.1 Pro (preview)GoogleRating 1499 ±401487rank 10–26$2$121.05MGoogle Released 2026-⁠02 Price $2 / $12 Length 1.05M
6–25GPT-5.6 SolOpenAIRating 1498 ±601485rank 10–30$4$201.05MOpenAI Released 2026-⁠07 Price $4 / $20 Length 1.05M
6–32Muse Spark 1.3MetaRating 1497 ±7+11496rank 3–15$1.25$4.251.05MMeta Released 2026-⁠09 Week change +1 Price $1.25 / $4.25 Length 1.05M
8–33Claude Opus 4.5AnthropicRating 1495 ±701474rank 23–46$5$25200KAnthropic Released 2025-⁠11 Price $5 / $25 Length 200K
6–49MiMo-V2.6 Pro⁠XiaomiRating 1494 ±15+11480rank 10–44$0.435$0.871.05MXiaomi Released 2026-⁠09 Week change +1 Price $0.435 / $0.87 Length 1.05M
9–36Claude Sonnet 4.6AnthropicRating 1492 ±501472rank 24–49$3$151MAnthropic Released 2026-⁠02 Price $3 / $15 Length 1M
8–39Qwen3.8 MaxAlibabaRating 1492 ±601483rank 10–36$2$61MAlibaba Released 2026-⁠08 Price $2 / $6 Length 1M
6–52Qwen3.7 Max (preview)AlibabaRating 1491 ±1501474rank 15–53————Alibaba Released — Price — Length —
9–43Gemini 3 ProGoogleRating 1491 ±601486rank 10–29——1.05MGoogle Released 2025-⁠11 Price — Length 1.05M
9–49GPT-6 AstraOpenAIRating 1489 ±9+11476rank 17–44$10$501.05MOpenAI Released 2026-⁠09 Week change +1 Price $10 / $50 Length 1.05M
8–50GPT-6.1 SolOpenAIRating 1489 ±11−41480rank 10–41$2$101.05MOpenAI Released 2026-⁠09 Week change −4 Price $2 / $10 Length 1.05M
9–49Muse Spark 1.2MetaRating 1488 ±10−61491rank 6–25$1.25$4.251.05MMeta Released 2026-⁠08 Week change −6 Price $1.25 / $4.25 Length 1.05M
14–47GPT-5.5OpenAIRating 1487 ±501482rank 12–36$5$301.05MOpenAI Released 2026-⁠04 Price $5 / $30 Length 1.05M
14–49GLM-5.2⁠Z.aiRating 1486 ±501475rank 19–43$1.4$4.41MZ.ai Released 2026-⁠06 Price $1.4 / $4.4 Length 1M
14–48MiMo-V2.5 Pro⁠XiaomiRating 1486 ±5−11466rank 34–53$0.435$0.871.05MXiaomi Released 2026-⁠04 Week change −1 Price $0.435 / $0.87 Length 1.05M
14–49GLM-5.3⁠Z.aiRating 1486 ±701481rank 11–38$1.4$4.41MZ.ai Released 2026-⁠08 Price $1.4 / $4.4 Length 1M
14–49Claude Sonnet 4.5AnthropicRating 1485 ±501456rank 49–69$3$15200KAnthropic Released 2025-⁠09 Price $3 / $15 Length 200K
14–49Gemini 3.6 FlashGoogleRating 1485 ±601483rank 10–35$0.75$3.751.05MGoogle Released 2026-⁠07 Price $0.75 / $3.75 Length 1.05M
14–49Claude Opus 4.1AnthropicRating 1485 ±601450rank 54–80——200KAnthropic Released 2025-⁠08 Price — Length 200K
18–51Gemini 3.5 FlashGoogleRating 1482 ±501477rank 18–41$1.5$91.05MGoogle Released 2026-⁠05 Price $1.5 / $9 Length 1.05M
19–52GPT-5.4OpenAIRating 1481 ±501475rank 19–42$2.5$151.05MOpenAI Released 2026-⁠03 Price $2.5 / $15 Length 1.05M
18–54Qwen3.5 Max (preview)AlibabaRating 1481 ±701465rank 36–60————Alibaba Released — Price — Length —
18–52GLM-5.3 Flash⁠Z.aiRating 1481 ±6−11476rank 19–43$0.15$0.51MZ.ai Released 2026-⁠08 Week change −1 Price $0.15 / $0.5 Length 1M
19–52Claude Sonnet 5AnthropicRating 1481 ±501461rank 41–64$2$101MAnthropic Released 2026-⁠06 Price $2 / $10 Length 1M
16–57DeepSeek-V4.1 Flash⁠DeepSeekRating 1481 ±8−11476rank 17–46——1MDeepSeek Released 2026-⁠09 Week change −1 Price — Length 1M
20–52GLM-5.1⁠Z.aiRating 1480 ±501465rank 36–53$1.4$4.4200KZ.ai Released 2026-⁠04 Price $1.4 / $4.4 Length 200K
20–53Muse Spark 1.1MetaRating 1480 ±5−11490rank 8–23$1.25$4.251MMeta Released 2026-⁠07 Week change −1 Price $1.25 / $4.25 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