Android Bench Updates Model Leaderboard
Ars Technica AI · rss · 2026-07-09
Google updated Android Bench, its benchmark for evaluating Android app development capabilities, adding several new models and evaluation dimensions.
This update incorporates cost and efficiency metrics alongside open-weight models, helping developers comprehensively compare LLM performance on Android tasks. Google also invites developers to run tests and provide feedback to shape the benchmark's future.
Newly added models include: Claude Fable 5, Claude Sonnet 5, Claude Opus 4.8, GLM 5.2, Kimi K2.7 Code, MiniMax M3, Qwen 3.7 Plus, Qwen 3.7 Max. The article concludes that Gemini still trails some competing models on this leaderboard.
More from Models
- OpenAI rolls out voice in GPT-Live, but the UI obscures search and reasoning — Graham_dePenros · 2026-07-22
- Moonshot’s Kimi K3 sets a new open-weights ECI record at 156 — scaling01 · 2026-07-22
- Nanbeige4.2-3B launches as a 3B Looped Transformer model that beats larger baselines — Wooden-Deer-1276 · 2026-07-22
- A post says six companies now beat Google’s best LLM, including two open-source models — soham_btw · 2026-07-22
- Google says Gemini 3.5 Pro is in testing and Gemini 4 is already pre-training — Wide-Ad1564 · 2026-07-22
- Gemini 3.5 Flash Lite Tested: Not Frontier-Optimal, but Hits 350 tok/s — brandon_galang · 2026-07-22