--- title: "Kimi K3.1 Pro benchmark: 76.7/100 at $1.89 per browser task" description: "Kimi K3.1 Pro scores 76.7/100 on 180 real browser tasks, #8 of 40, at $1.89 per task. GPT-6.1 Sol medium scores 2.9 points higher for 1.5× less." canonical: "https://browser-use.com/benchmarks/models/kimi-k3-1-pro" --- # Kimi K3.1 Pro benchmark: 76.7/100 at $1.89 per browser task Browser Use Bench v2.1 | 180 tasks | October 29, 2026 ## Kimi K3.1 Pro on real browser tasks. #8 of 40. GPT-6.1 Sol medium scores 2.9 points higher for 1.5× less. Ran on Moonshot's fast tier through OpenRouter; cost repriced to Moonshot's standard per-token price. Score76.7 Cost / task$1.89 Median time9 min 45505560657075808510¢20¢50¢$1$2$5$10model cost per task, log scalescore / 100GPT-6.1 Sol81.3GPT-6 Sol79.4GPT-6.1 Terra79.0GPT-6 Astra77.9Kimi K3.1 Pro76.7DeepSeek V4.1 Flash 101775.0Opus 5.575.0Grok 4.773.3Browser Use72.9Sonnet 5.572.7Fable 5.172.0DeepSeek V4.1 Flash70.9GPT-5.6 Luna69.6Haiku 5.569.5GPT-6 Luna69.2Opus 566.8GLM 5.3 FlashX59.7MiniMax M3.1 Flash50.6 180 long tasks on live websites, the same for every model, run in the open-source BrowserCode harness (Browser Use's own agent runs in ours). Mean weighted rubric score per task, 0-100. Estimated model cost per task in USD. Excludes search, judge, browser and runner costs. Runner and encrypted tasks: [github.com/browser-use/benchmark](https://github.com/browser-use/benchmark). Compare |[full leaderboard](https://browser-use.com/benchmarks/agents) - [GPT-6.1 Terra79.0](https://browser-use.com/benchmarks/models/gpt-6-1-terra) - [GPT-6.1 Sol81.3](https://browser-use.com/benchmarks/models/gpt-6-1-sol) - [GPT-6 Astra77.9](https://browser-use.com/benchmarks/models/gpt-6-astra) - [GPT-6 Sol79.4](https://browser-use.com/benchmarks/models/gpt-6-sol) - [GPT-5.6 Luna69.6](https://browser-use.com/benchmarks/models/gpt-5-6-luna) - [GPT-6 Luna69.2](https://browser-use.com/benchmarks/models/gpt-6-luna) - [Opus 5.575.0](https://browser-use.com/benchmarks/models/claude-opus-5-5) - [Opus 566.8](https://browser-use.com/benchmarks/models/claude-opus-5) - [Sonnet 5.572.7](https://browser-use.com/benchmarks/models/claude-sonnet-5-5) - [Fable 5.172.0](https://browser-use.com/benchmarks/models/claude-fable-5-1) - [Haiku 5.569.5](https://browser-use.com/benchmarks/models/claude-haiku-5-5) - [Grok 4.773.3](https://browser-use.com/benchmarks/models/grok-4-7) - [DeepSeek V4.1 Flash70.9](https://browser-use.com/benchmarks/models/deepseek-v4-1-flash) - [DeepSeek V4.1 Flash 101775.0](https://browser-use.com/benchmarks/models/deepseek-v4-1-flash-1017) - [GLM 5.3 FlashX59.7](https://browser-use.com/benchmarks/models/glm-5-3-flashx) - [MiniMax M3.1 Flash50.6](https://browser-use.com/benchmarks/models/minimax-m3-1-flash) [Run your tasks in the cloud](https://cloud.browser-use.com/v4?utm_source=browser-use&utm_medium=benchmark-models) --- BROWSER USE - Browser Use Agents: give Browser Use a task and receive completed work. API V4 is current for new integrations. - Browser Infrastructure: connect your agent or automation to managed browsers through SDK, REST, or CDP. Starts at $0.02/browser-hour. - Developer tools: Open Source, Browser Harness, SDK, and MCP support the two products above. [Developer Index](https://browser-use.com/index.md) [Product Map](https://browser-use.com/llms.txt) [Full Product Context](https://browser-use.com/llms-full.txt) [Pricing](https://browser-use.com/pricing.md) [Cloud Docs](https://docs.browser-use.com/cloud/quickstart) [Open Source Docs](https://docs.browser-use.com/open-source/introduction)