Skip to main content

Human ratings

Coding (human ratings)

A category computed only from questions identified as programming questions from cues such as code blocks and programming language names.

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 1500 to 1600Week
change
OverallInput $
/1M
Output $
/1M
ContextSupportsWeightsReleasedPrice and specs
1–18Gemini 4 ArgonGoogleRating 1552 ±13−91517rank 1–3$2$101.05MGoogle Released 2026-⁠09 Week change −9 Price $2 / $10 Length 1.05M
1–13Claude Fable 5AnthropicRating 1551 ±601503rank 2–9$10$501MAnthropic Released 2026-⁠06 Price $10 / $50 Length 1M
1–12Claude Opus 4.7AnthropicRating 1550 ±601501rank 2–10$5$251MAnthropic Released 2026-⁠04 Price $5 / $25 Length 1M
1–21Claude Opus 5.5AnthropicRating 1548 ±13+31509rank 1–7$4$201MAnthropic Released 2026-⁠09 Week change +3 Price $4 / $20 Length 1M
1–14Claude Opus 4.6AnthropicRating 1547 ±5−11503rank 2–9$5$251MAnthropic Released 2026-⁠02 Week change −1 Price $5 / $25 Length 1M
1–28Muse WonderMetaRating 1545 ±16−131509rank 1–8$4$201.05MMeta Released 2026-⁠10 Week change −13 Price $4 / $20 Length 1.05M
1–25GPT-6 AstraOpenAIRating 1543 ±1101476rank 17–44$10$501.05MOpenAI Released 2026-⁠09 Price $10 / $50 Length 1.05M
1–27Muse Spark 1.2MetaRating 1541 ±12+31491rank 6–25$1.25$4.251.05MMeta Released 2026-⁠08 Week change +3 Price $1.25 / $4.25 Length 1.05M
1–25Kimi K3⁠MoonshotRating 1539 ±701487rank 8–27$3$151.05MMoonshot Released 2026-⁠07 Price $3 / $15 Length 1.05M
1–47MiMo-V2.6 Pro⁠XiaomiRating 1538 ±18+11480rank 10–44$0.435$0.871.05MXiaomi Released 2026-⁠09 Week change +1 Price $0.435 / $0.87 Length 1.05M
1–30Claude Fable 5.1AnthropicRating 1537 ±11+21503rank 2–10$10$501MAnthropic Released 2026-⁠09 Week change +2 Price $10 / $50 Length 1M
1–40GPT-6.1 SolOpenAIRating 1537 ±15−11480rank 10–41$2$101.05MOpenAI Released 2026-⁠09 Week change −1 Price $2 / $10 Length 1.05M
2–29Muse Spark 1.3MetaRating 1536 ±9−11496rank 3–15$1.25$4.251.05MMeta Released 2026-⁠09 Week change −1 Price $1.25 / $4.25 Length 1.05M
4–28Claude Opus 5AnthropicRating 1534 ±6+11491rank 8–22$5$251MAnthropic Released 2026-⁠07 Week change +1 Price $5 / $25 Length 1M
4–29GPT-5.6 SolOpenAIRating 1534 ±7−11485rank 10–30$4$201.05MOpenAI Released 2026-⁠07 Week change −1 Price $4 / $20 Length 1.05M
4–29Claude Opus 4.8AnthropicRating 1533 ±601481rank 12–36$5$251MAnthropic Released 2026-⁠05 Price $5 / $25 Length 1M
5–31Muse Spark 1.1MetaRating 1533 ±601490rank 8–23$1.25$4.251MMeta Released 2026-⁠07 Price $1.25 / $4.25 Length 1M
5–39Claude Opus 4.5AnthropicRating 1530 ±701474rank 23–46$5$25200KAnthropic Released 2025-⁠11 Price $5 / $25 Length 200K
5–49Muse SparkMetaRating 1529 ±1001489rank 8–27———Meta Released 2026-⁠04 Price — Length —
6–39Claude Sonnet 4.6AnthropicRating 1528 ±601472rank 24–49$3$151MAnthropic Released 2026-⁠02 Price $3 / $15 Length 1M
6–43Gemini 3.8 FlashGoogleRating 1528 ±7+11496rank 4–15$0.75$3.751.05MGoogle Released 2026-⁠09 Week change +1 Price $0.75 / $3.75 Length 1.05M
4–58Claude Sonnet 5.5AnthropicRating 1528 ±13+11478rank 14–44$2$101MAnthropic Released 2026-⁠09 Week change +1 Price $2 / $10 Length 1M
6–51GLM-5.3 Flash⁠Z.aiRating 1525 ±701476rank 19–43$0.15$0.51MZ.ai Released 2026-⁠08 Price $0.15 / $0.5 Length 1M
3–73Qwen3.7 Max (preview)AlibabaRating 1524 ±1801474rank 15–53————Alibaba Released — Price — Length —
8–55Qwen3.8 MaxAlibabaRating 1524 ±7+11483rank 10–36$2$61MAlibaba Released 2026-⁠08 Week change +1 Price $2 / $6 Length 1M
6–60DeepSeek-V4.1 Flash⁠DeepSeekRating 1523 ±10−21476rank 17–46——1MDeepSeek Released 2026-⁠09 Week change −2 Price — Length 1M
16–55Gemini 3.1 Pro (preview)GoogleRating 1522 ±501487rank 10–26$2$121.05MGoogle Released 2026-⁠02 Price $2 / $12 Length 1.05M
9–63GLM-5.3⁠Z.aiRating 1521 ±8+11481rank 11–38$1.4$4.41MZ.ai Released 2026-⁠08 Week change +1 Price $1.4 / $4.4 Length 1M
15–58GPT-5.4OpenAIRating 1521 ±601475rank 19–42$2.5$151.05MOpenAI Released 2026-⁠03 Price $2.5 / $15 Length 1.05M
16–58MiMo-V2.5 Pro⁠XiaomiRating 1521 ±5−11466rank 34–53$0.435$0.871.05MXiaomi Released 2026-⁠04 Week change −1 Price $0.435 / $0.87 Length 1.05M
11–62Gemini 3.7 FlashGoogleRating 1520 ±7+41490rank 8–25$0.75$3.751.05MGoogle Released 2026-⁠08 Week change +4 Price $0.75 / $3.75 Length 1.05M
16–60Claude Sonnet 5AnthropicRating 1520 ±601461rank 41–64$2$101MAnthropic Released 2026-⁠06 Price $2 / $10 Length 1M
8–65GPT-6 SolOpenAIRating 1519 ±11+11459rank 41–71$2$101.05MOpenAI Released 2026-⁠09 Week change +1 Price $2 / $10 Length 1.05M
16–61GPT-5.5OpenAIRating 1519 ±601482rank 12–36$5$301.05MOpenAI Released 2026-⁠04 Price $5 / $30 Length 1.05M
16–60Claude Sonnet 4.5AnthropicRating 1519 ±501456rank 49–69$3$15200KAnthropic Released 2025-⁠09 Price $3 / $15 Length 200K
16–63Gemini 3.6 FlashGoogleRating 1518 ±701483rank 10–35$0.75$3.751.05MGoogle Released 2026-⁠07 Price $0.75 / $3.75 Length 1.05M
16–63GPT-5.6 TerraOpenAIRating 1518 ±6+11467rank 28–53$2$121.05MOpenAI Released 2026-⁠07 Week change +1 Price $2 / $12 Length 1.05M
16–65Gemini 3 ProGoogleRating 1517 ±701486rank 10–29——1.05MGoogle Released 2025-⁠11 Price — Length 1.05M
18–65Kimi K2.6⁠MoonshotRating 1516 ±701461rank 41–65$0.95$4262.1KMoonshot Released 2026-⁠04 Price $0.95 / $4 Length 262.1K
19–68GPT-5.2 ChatOpenAIRating 1515 ±701476rank 19–42——128KOpenAI Released 2026-⁠02 Price — Length 128K
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