benchmark results

Winsage
July 16, 2026
Valve has released new Windows drivers for its Steam Machine console, improving user experience. Benchmark results from ETA Prime indicate that after installing Windows 11, the Steam Machine operates smoothly with all hardware components functioning well. The GPU is an AMD Radeon RX 7600, and the machine has been upgraded to 64 GB of memory. In performance comparisons, Windows outperforms SteamOS in the Geekbench 6 multi-thread benchmark by 22%, while single-core results are similar. In Cinebench 2024, the Steam Machine scores 99 points in single-core and 554 points in multi-core, trailing behind Apple's M1 Max and AMD Ryzen 5800X in multi-thread performance. Gaming performance shows a competitive edge between the two operating systems. Windows has a slight advantage in Shadow of the Tomb Raider at 4K and 1080p, while SteamOS leads at 1440p. In Cyberpunk 2077, SteamOS outperforms Windows by 8.8% at 4K and 4.7% at 1440p. At 4K, both struggle, with SteamOS averaging 18 FPS and Windows 20 FPS. In Horizon Zero Dawn Remastered, Windows has a 7.1% advantage, while SteamOS is faster at 1440p and Windows leads at 1080p. Running Windows on the Steam Machine is a viable option, supporting Valve's claim that it functions as a standard PC, though there are other factors to consider beyond gaming performance.
AppWizard
June 13, 2026
Google has released benchmark results for evaluating AI models in Android coding, revealing that the Gemini 3.5 Flash is the most resource-intensive model but ranks sixth overall. The benchmarks indicate that Gemini 3.5 Flash has higher latency and a 9% performance gap compared to its predecessor, Gemini 3.1 Pro Preview, despite being marketed as a faster alternative. In terms of cost, Gemini 3.5 Flash averages 355.9 tokens per benchmark run at approximately 7.1, while Gemini 3.1 Pro Preview uses only 73.3 tokens at about a third of that cost. The top-ranked models include GPT 5.5, GPT 5.4, and Gemini 3.1 Pro Preview, while Claude Opus 4.7 ranks fourth. The rankings feature both open-weight and closed-weight models, with the list remaining consistent since the last release, except for the removal of GPT 5.3 Codex.
Search