Skip to main content

Human ratings

Software and IT (human ratings)

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

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 1600Week
change
OverallInput $
/1M
Output $
/1M
ContextSupportsWeightsReleasedPrice and specs
1–9Gemini 4 ArgonGoogleRating 1549 ±10−141517rank 1–3$2$101.05MGoogle Released 2026-⁠09 Week change −14 Price $2 / $10 Length 1.05M
1–11Claude Opus 4.7AnthropicRating 1540 ±501501rank 2–10$5$251MAnthropic Released 2026-⁠04 Price $5 / $25 Length 1M
1–11Claude Fable 5AnthropicRating 1538 ±601503rank 2–9$10$501MAnthropic Released 2026-⁠06 Price $10 / $50 Length 1M
1–18Claude Opus 5.5AnthropicRating 1538 ±11+11509rank 1–7$4$201MAnthropic Released 2026-⁠09 Week change +1 Price $4 / $20 Length 1M
1–11Claude Opus 4.6AnthropicRating 1537 ±5−11503rank 2–9$5$251MAnthropic Released 2026-⁠02 Week change −1 Price $5 / $25 Length 1M
1–24Muse WonderMetaRating 1534 ±13−61509rank 1–8$4$201.05MMeta Released 2026-⁠10 Week change −6 Price $4 / $20 Length 1.05M
1–22Muse Spark 1.2MetaRating 1532 ±10+21491rank 6–25$1.25$4.251.05MMeta Released 2026-⁠08 Week change +2 Price $1.25 / $4.25 Length 1.05M
2–23Claude Fable 5.1AnthropicRating 1530 ±9+21503rank 2–10$10$501MAnthropic Released 2026-⁠09 Week change +2 Price $10 / $50 Length 1M
1–29GPT-6.1 SolOpenAIRating 1528 ±12−21480rank 10–41$2$101.05MOpenAI Released 2026-⁠09 Week change −2 Price $2 / $10 Length 1.05M
1–34MiMo-V2.6 Pro⁠XiaomiRating 1528 ±14+11480rank 10–44$0.435$0.871.05MXiaomi Released 2026-⁠09 Week change +1 Price $0.435 / $0.87 Length 1.05M
2–24Muse Spark 1.3MetaRating 1528 ±8−21496rank 3–15$1.25$4.251.05MMeta Released 2026-⁠09 Week change −2 Price $1.25 / $4.25 Length 1.05M
5–25Muse Spark 1.1MetaRating 1525 ±6−11490rank 8–23$1.25$4.251MMeta Released 2026-⁠07 Week change −1 Price $1.25 / $4.25 Length 1M
5–26Claude Opus 5AnthropicRating 1523 ±5+11491rank 8–22$5$251MAnthropic Released 2026-⁠07 Week change +1 Price $5 / $25 Length 1M
5–27Claude Opus 4.8AnthropicRating 1523 ±501481rank 12–36$5$251MAnthropic Released 2026-⁠05 Price $5 / $25 Length 1M
5–29Kimi K3⁠MoonshotRating 1523 ±6−21487rank 8–27$3$151.05MMoonshot Released 2026-⁠07 Week change −2 Price $3 / $15 Length 1.05M
5–29GPT-5.6 SolOpenAIRating 1523 ±6−11485rank 10–30$4$201.05MOpenAI Released 2026-⁠07 Week change −1 Price $4 / $20 Length 1.05M
5–34GPT-6 AstraOpenAIRating 1523 ±901476rank 17–44$10$501.05MOpenAI Released 2026-⁠09 Price $10 / $50 Length 1.05M
5–34Muse SparkMetaRating 1523 ±801489rank 8–27———Meta Released 2026-⁠04 Price — Length —
6–40Gemini 3.8 FlashGoogleRating 1518 ±6+11496rank 4–15$0.75$3.751.05MGoogle Released 2026-⁠09 Week change +1 Price $0.75 / $3.75 Length 1.05M
6–53Claude Sonnet 5.5AnthropicRating 1516 ±11+11478rank 14–44$2$101MAnthropic Released 2026-⁠09 Week change +1 Price $2 / $10 Length 1M
7–45GLM-5.3 Flash⁠Z.aiRating 1515 ±601476rank 19–43$0.15$0.51MZ.ai Released 2026-⁠08 Price $0.15 / $0.5 Length 1M
10–43Claude Sonnet 4.6AnthropicRating 1514 ±501472rank 24–49$3$151MAnthropic Released 2026-⁠02 Price $3 / $15 Length 1M
6–53DeepSeek-V4.1 Flash⁠DeepSeekRating 1514 ±9−21476rank 17–46——1MDeepSeek Released 2026-⁠09 Week change −2 Price — Length 1M
8–53GLM-5.3⁠Z.aiRating 1513 ±7+11481rank 11–38$1.4$4.41MZ.ai Released 2026-⁠08 Week change +1 Price $1.4 / $4.4 Length 1M
13–44Gemini 3.1 Pro (preview)GoogleRating 1513 ±401487rank 10–26$2$121.05MGoogle Released 2026-⁠02 Price $2 / $12 Length 1.05M
11–53Qwen3.8 MaxAlibabaRating 1512 ±601483rank 10–36$2$61MAlibaba Released 2026-⁠08 Price $2 / $6 Length 1M
13–53Claude Opus 4.5AnthropicRating 1512 ±601474rank 23–46$5$25200KAnthropic Released 2025-⁠11 Price $5 / $25 Length 200K
12–53Gemini 3.7 FlashGoogleRating 1511 ±7+21490rank 8–25$0.75$3.751.05MGoogle Released 2026-⁠08 Week change +2 Price $0.75 / $3.75 Length 1.05M
16–53GPT-5.5OpenAIRating 1511 ±501482rank 12–36$5$301.05MOpenAI Released 2026-⁠04 Price $5 / $30 Length 1.05M
16–54Gemini 3.6 FlashGoogleRating 1510 ±601483rank 10–35$0.75$3.751.05MGoogle Released 2026-⁠07 Price $0.75 / $3.75 Length 1.05M
6–69Qwen3.7 Max (preview)AlibabaRating 1510 ±1501474rank 15–53————Alibaba Released — Price — Length —
16–55GPT-5.2 ChatOpenAIRating 1510 ±601476rank 19–42——128KOpenAI Released 2026-⁠02 Price — Length 128K
16–55Gemini 3 ProGoogleRating 1509 ±601486rank 10–29——1.05MGoogle Released 2025-⁠11 Price — Length 1.05M
19–55MiMo-V2.5 Pro⁠XiaomiRating 1509 ±5−21466rank 34–53$0.435$0.871.05MXiaomi Released 2026-⁠04 Week change −2 Price $0.435 / $0.87 Length 1.05M
19–56ERNIE 5.1BaiduRating 1507 ±601467rank 26–53——119K—Baidu Released — Price — Length 119K
19–56GPT-5.6 TerraOpenAIRating 1507 ±6+11467rank 28–53$2$121.05MOpenAI Released 2026-⁠07 Week change +1 Price $2 / $12 Length 1.05M
19–56GPT-5.4OpenAIRating 1507 ±501475rank 19–42$2.5$151.05MOpenAI Released 2026-⁠03 Price $2.5 / $15 Length 1.05M
19–56GLM-5.2⁠Z.aiRating 1506 ±5+11475rank 19–43$1.4$4.41MZ.ai Released 2026-⁠06 Week change +1 Price $1.4 / $4.4 Length 1M
16–67GPT-6 SolOpenAIRating 1505 ±9+21459rank 41–71$2$101.05MOpenAI Released 2026-⁠09 Week change +2 Price $2 / $10 Length 1.05M
20–61Claude Sonnet 5AnthropicRating 1505 ±5+11461rank 41–64$2$101MAnthropic Released 2026-⁠06 Week change +1 Price $2 / $10 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