Skip to main content

Human ratings

Overall (human ratings)

A rating built from all votes cast by users who compare anonymous answers to the same question and pick the better one.

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
Input $
/1M
Output $
/1M
ContextSupportsWeightsReleasedPrice and specs
1–3Gemini 4 ArgonGoogleRating 1517 ±7−8$2$101.05MGoogle Released 2026-⁠09 Week change −8 Price $2 / $10 Length 1.05M
1–7Claude Opus 5.5AnthropicRating 1509 ±7+1$4$201MAnthropic Released 2026-⁠09 Week change +1 Price $4 / $20 Length 1M
1–8Muse WonderMetaRating 1509 ±8−4$4$201.05MMeta Released 2026-⁠10 Week change −4 Price $4 / $20 Length 1.05M
2–9Claude Fable 5AnthropicRating 1503 ±40$10$501MAnthropic Released 2026-⁠06 Price $10 / $50 Length 1M
2–10Claude Fable 5.1AnthropicRating 1503 ±6+3$10$501MAnthropic Released 2026-⁠09 Week change +3 Price $10 / $50 Length 1M
2–9Claude Opus 4.6AnthropicRating 1503 ±30$5$251MAnthropic Released 2026-⁠02 Price $5 / $25 Length 1M
2–10Claude Opus 4.7AnthropicRating 1501 ±40$5$251MAnthropic Released 2026-⁠04 Price $5 / $25 Length 1M
4–15Gemini 3.8 FlashGoogleRating 1496 ±4−1$0.75$3.751.05MGoogle Released 2026-⁠09 Week change −1 Price $0.75 / $3.75 Length 1.05M
3–15Muse Spark 1.3MetaRating 1496 ±5+1$1.25$4.251.05MMeta Released 2026-⁠09 Week change +1 Price $1.25 / $4.25 Length 1.05M
6–25Muse Spark 1.2MetaRating 1491 ±7−3$1.25$4.251.05MMeta Released 2026-⁠08 Week change −3 Price $1.25 / $4.25 Length 1.05M
8–22Claude Opus 5AnthropicRating 1491 ±5+1$5$251MAnthropic Released 2026-⁠07 Week change +1 Price $5 / $25 Length 1M
8–23Muse Spark 1.1MetaRating 1490 ±40$1.25$4.251MMeta Released 2026-⁠07 Price $1.25 / $4.25 Length 1M
8–25Gemini 3.7 FlashGoogleRating 1490 ±5+2$0.75$3.751.05MGoogle Released 2026-⁠08 Week change +2 Price $0.75 / $3.75 Length 1.05M
8–27Muse SparkMetaRating 1489 ±60———Meta Released 2026-⁠04 Price — Length —
8–27Kimi K3⁠MoonshotRating 1487 ±4−1$3$151.05MMoonshot Released 2026-⁠07 Week change −1 Price $3 / $15 Length 1.05M
10–26Gemini 3.1 Pro (preview)GoogleRating 1487 ±30$2$121.05MGoogle Released 2026-⁠02 Price $2 / $12 Length 1.05M
10–29Gemini 3 ProGoogleRating 1486 ±40——1.05MGoogle Released 2025-⁠11 Price — Length 1.05M
10–30GPT-5.6 SolOpenAIRating 1485 ±40$4$201.05MOpenAI Released 2026-⁠07 Price $4 / $20 Length 1.05M
10–35Gemini 3.6 FlashGoogleRating 1483 ±40$0.75$3.751.05MGoogle Released 2026-⁠07 Price $0.75 / $3.75 Length 1.05M
10–36Qwen3.8 MaxAlibabaRating 1483 ±5+1$2$61MAlibaba Released 2026-⁠08 Week change +1 Price $2 / $6 Length 1M
12–36GPT-5.5OpenAIRating 1482 ±40$5$301.05MOpenAI Released 2026-⁠04 Price $5 / $30 Length 1.05M
12–36Claude Opus 4.8AnthropicRating 1481 ±40$5$251MAnthropic Released 2026-⁠05 Price $5 / $25 Length 1M
11–38GLM-5.3⁠Z.aiRating 1481 ±5+2$1.4$4.41MZ.ai Released 2026-⁠08 Week change +2 Price $1.4 / $4.4 Length 1M
10–41GPT-6.1 SolOpenAIRating 1480 ±7−4$2$101.05MOpenAI Released 2026-⁠09 Week change −4 Price $2 / $10 Length 1.05M
10–44MiMo-V2.6 Pro⁠XiaomiRating 1480 ±9+1$0.435$0.871.05MXiaomi Released 2026-⁠09 Week change +1 Price $0.435 / $0.87 Length 1.05M
14–44Claude Sonnet 5.5AnthropicRating 1478 ±7+2$2$101MAnthropic Released 2026-⁠09 Week change +2 Price $2 / $10 Length 1M
18–41Gemini 3.5 FlashGoogleRating 1477 ±40$1.5$91.05MGoogle Released 2026-⁠05 Price $1.5 / $9 Length 1.05M
17–44GPT-6 AstraOpenAIRating 1476 ±60$10$501.05MOpenAI Released 2026-⁠09 Price $10 / $50 Length 1.05M
17–46DeepSeek-V4.1 Flash⁠DeepSeekRating 1476 ±6+1——1MDeepSeek Released 2026-⁠09 Week change +1 Price — Length 1M
19–43GLM-5.3 Flash⁠Z.aiRating 1476 ±5+2$0.15$0.51MZ.ai Released 2026-⁠08 Week change +2 Price $0.15 / $0.5 Length 1M
19–42GPT-5.2 ChatOpenAIRating 1476 ±40——128KOpenAI Released 2026-⁠02 Price — Length 128K
19–43GLM-5.2⁠Z.aiRating 1475 ±40$1.4$4.41MZ.ai Released 2026-⁠06 Price $1.4 / $4.4 Length 1M
19–42GPT-5.4OpenAIRating 1475 ±40$2.5$151.05MOpenAI Released 2026-⁠03 Price $2.5 / $15 Length 1.05M
19–45Grok 4.20 (beta1)xAIRating 1475 ±50————xAI Released — Price — Length —
15–53Qwen3.7 Max (preview)AlibabaRating 1474 ±100————Alibaba Released — Price — Length —
23–46Claude Opus 4.5AnthropicRating 1474 ±40$5$25200KAnthropic Released 2025-⁠11 Price $5 / $25 Length 200K
20–50GPT-5.5 InstantOpenAIRating 1473 ±50———OpenAI Released 2026-⁠05 Price — Length —
23–49Gemini 3 FlashGoogleRating 1473 ±40——1.05MGoogle Released 2025-⁠12 Price — Length 1.05M
24–49Claude Sonnet 4.6AnthropicRating 1472 ±40$3$151MAnthropic Released 2026-⁠02 Price $3 / $15 Length 1M
24–50Grok 4.20 Beta Reasoning (0309)xAIRating 1472 ±40——2M—xAI Released — Price — Length 2M
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