Skip to main content

Human ratings

Business and finance (human ratings)

Among the occupational fields questions are sorted into, a category computed only from questions in business and finance.

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
1–17Gemini 4 ArgonGoogleRating 1509 ±15−121517rank 1–3$2$101.05MGoogle Released 2026-⁠09 Week change −12 Price $2 / $10 Length 1.05M
1–10Claude Opus 4.7AnthropicRating 1508 ±601501rank 2–10$5$251MAnthropic Released 2026-⁠04 Price $5 / $25 Length 1M
1–24Muse Spark 1.2MetaRating 1502 ±14−51491rank 6–25$1.25$4.251.05MMeta Released 2026-⁠08 Week change −5 Price $1.25 / $4.25 Length 1.05M
1–21Muse Spark 1.3MetaRating 1501 ±10−31496rank 3–15$1.25$4.251.05MMeta Released 2026-⁠09 Week change −3 Price $1.25 / $4.25 Length 1.05M
1–17Claude Fable 5AnthropicRating 1500 ±7−11503rank 2–9$10$501MAnthropic Released 2026-⁠06 Week change −1 Price $10 / $50 Length 1M
1–17Claude Opus 4.6AnthropicRating 1500 ±6−11503rank 2–9$5$251MAnthropic Released 2026-⁠02 Week change −1 Price $5 / $25 Length 1M
1–34Muse WonderMetaRating 1498 ±19−21509rank 1–8$4$201.05MMeta Released 2026-⁠10 Week change −2 Price $4 / $20 Length 1.05M
1–34Claude Opus 5.5AnthropicRating 1494 ±14+21509rank 1–7$4$201MAnthropic Released 2026-⁠09 Week change +2 Price $4 / $20 Length 1M
2–27Muse Spark 1.1MetaRating 1491 ±7−11490rank 8–23$1.25$4.251MMeta Released 2026-⁠07 Week change −1 Price $1.25 / $4.25 Length 1M
2–27GPT-5.5OpenAIRating 1490 ±601482rank 12–36$5$301.05MOpenAI Released 2026-⁠04 Price $5 / $30 Length 1.05M
1–34Muse SparkMetaRating 1490 ±1201489rank 8–27———Meta Released 2026-⁠04 Price — Length —
2–31Claude Opus 4.8AnthropicRating 1489 ±601481rank 12–36$5$251MAnthropic Released 2026-⁠05 Price $5 / $25 Length 1M
2–34Kimi K3⁠MoonshotRating 1487 ±8−11487rank 8–27$3$151.05MMoonshot Released 2026-⁠07 Week change −1 Price $3 / $15 Length 1.05M
2–34GPT-5.6 SolOpenAIRating 1487 ±8+11485rank 10–30$4$201.05MOpenAI Released 2026-⁠07 Week change +1 Price $4 / $20 Length 1.05M
1–52GPT-6.1 SolOpenAIRating 1485 ±17+21480rank 10–41$2$101.05MOpenAI Released 2026-⁠09 Week change +2 Price $2 / $10 Length 1.05M
5–34Claude Opus 5AnthropicRating 1485 ±701491rank 8–22$5$251MAnthropic Released 2026-⁠07 Price $5 / $25 Length 1M
2–40Qwen3.8 MaxAlibabaRating 1485 ±901483rank 10–36$2$61MAlibaba Released 2026-⁠08 Price $2 / $6 Length 1M
2–43Claude Fable 5.1AnthropicRating 1485 ±1101503rank 2–10$10$501MAnthropic Released 2026-⁠09 Price $10 / $50 Length 1M
5–39GPT-5.2 ChatOpenAIRating 1485 ±801476rank 19–42——128KOpenAI Released 2026-⁠02 Price — Length 128K
5–41Gemini 3.7 FlashGoogleRating 1484 ±9+11490rank 8–25$0.75$3.751.05MGoogle Released 2026-⁠08 Week change +1 Price $0.75 / $3.75 Length 1.05M
6–41GPT-5.4OpenAIRating 1482 ±601475rank 19–42$2.5$151.05MOpenAI Released 2026-⁠03 Price $2.5 / $15 Length 1.05M
7–41Claude Sonnet 4.6AnthropicRating 1482 ±601472rank 24–49$3$151MAnthropic Released 2026-⁠02 Price $3 / $15 Length 1M
6–44Gemini 3.8 FlashGoogleRating 1481 ±8+11496rank 4–15$0.75$3.751.05MGoogle Released 2026-⁠09 Week change +1 Price $0.75 / $3.75 Length 1.05M
9–44Gemini 3.1 Pro (preview)GoogleRating 1478 ±501487rank 10–26$2$121.05MGoogle Released 2026-⁠02 Price $2 / $12 Length 1.05M
6–59DeepSeek-V4.1 Flash⁠DeepSeekRating 1477 ±12+11476rank 17–46——1MDeepSeek Released 2026-⁠09 Week change +1 Price — Length 1M
5–66Claude Sonnet 5.5AnthropicRating 1476 ±16+101478rank 14–44$2$101MAnthropic Released 2026-⁠09 Week change +10 Price $2 / $10 Length 1M
7–54GPT-5.5 InstantOpenAIRating 1476 ±901473rank 20–50———OpenAI Released 2026-⁠05 Price — Length —
9–54ERNIE 5.1BaiduRating 1475 ±801467rank 26–53——119K—Baidu Released — Price — Length 119K
10–55Gemini 3 ProGoogleRating 1474 ±701486rank 10–29——1.05MGoogle Released 2025-⁠11 Price — Length 1.05M
9–59GLM-5.3⁠Z.aiRating 1474 ±901481rank 11–38$1.4$4.41MZ.ai Released 2026-⁠08 Price $1.4 / $4.4 Length 1M
7–66GPT-6 AstraOpenAIRating 1473 ±12+11476rank 17–44$10$501.05MOpenAI Released 2026-⁠09 Week change +1 Price $10 / $50 Length 1.05M
10–59Gemini 3.6 FlashGoogleRating 1473 ±801483rank 10–35$0.75$3.751.05MGoogle Released 2026-⁠07 Price $0.75 / $3.75 Length 1.05M
16–56Claude Opus 4.5AnthropicRating 1472 ±601474rank 23–46$5$25200KAnthropic Released 2025-⁠11 Price $5 / $25 Length 200K
16–59MiMo-V2.5 Pro⁠XiaomiRating 1471 ±601466rank 34–53$0.435$0.871.05MXiaomi Released 2026-⁠04 Price $0.435 / $0.87 Length 1.05M
16–64GLM-5.3 Flash⁠Z.aiRating 1470 ±801476rank 19–43$0.15$0.51MZ.ai Released 2026-⁠08 Price $0.15 / $0.5 Length 1M
16–67Grok 4.20 (beta1)xAIRating 1469 ±901475rank 19–45————xAI Released — Price — Length —
17–66Gemini 3 FlashGoogleRating 1469 ±801473rank 23–49——1.05MGoogle Released 2025-⁠12 Price — Length 1.05M
21–66Gemini 3.5 FlashGoogleRating 1468 ±701477rank 18–41$1.5$91.05MGoogle Released 2026-⁠05 Price $1.5 / $9 Length 1.05M
10–82DeepSeek-V4 Pro (2026-⁠08)⁠DeepSeekRating 1467 ±14+11465rank 30–64$0.66$1.981MDeepSeek Released 2026-⁠08 Week change +1 Price $0.66 / $1.98 Length 1M
21–68GPT-5.6 TerraOpenAIRating 1467 ±7+11467rank 28–53$2$121.05MOpenAI Released 2026-⁠07 Week change +1 Price $2 / $12 Length 1.05M
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