docs: show hard benchmark v2 in README

README.md

@@ -129,13 +129,9 @@ Check out the [library docs](https://docs.browser-use.com/open-source/introducti
 
 # Open Source vs Cloud
 
-<picture>
-  <source media="(prefers-color-scheme: light)" srcset="static/accuracy_by_model_light.png">
-  <source media="(prefers-color-scheme: dark)" srcset="static/accuracy_by_model_dark.png">
-  <img alt="BU Bench V1 - LLM Success Rates" src="static/accuracy_by_model_light.png" width="100%">
-</picture>
+<img alt="Browser Use Benchmark v2 - Mean rubric score by model and cost per task" src="static/hard_benchmark_v2.jpg" width="100%">
 
-We benchmark Browser Use across 100 real-world browser tasks. Full benchmark is open source: **[browser-use/benchmark](https://github.com/browser-use/benchmark)**.
+This [very hard benchmark](https://github.com/browser-use/benchmark) targets the hardest browser tasks. On easier tasks, even smaller models can achieve very high success rates. Results shown are from a 60-task subset of BU Bench V2.
 
 Browser Use is also **#1 on the [Odysseys leaderboard](https://odysseysbench.com/leaderboard)** with an 87.4% average, ahead of computer-use agents from OpenAI, Anthropic, Google, and Microsoft. Odysseys measures the agent's performance on 200 long-horizon web tasks.
 
@@ -145,7 +141,7 @@ Browser Use is also **#1 on the [Odysseys leaderboard](https://odysseysbench.com
 - We recommend pairing it with our [cloud browsers](https://docs.browser-use.com/open-source/customize/browser/remote) for leading stealth, proxy rotation, and scaling
 
 **Use the [Fully-Hosted Cloud Agent](https://cloud.browser-use.com?utm_source=github&utm_medium=readme-hosted-agent) (recommended)**
-- Much more powerful agent for complex tasks (see plot above)
+- Much more powerful agent for complex tasks
 - Easiest way to start and scale
 - Best stealth with proxy rotation and captcha solving
 - 1000+ integrations (Gmail, Slack, Notion, and more)