Qwen3.5 Flash: benchmarks, price and rank

Its headline results

The benchmarks that count most in the rating, with its place among the models measured the same way, and where each number came from.

• Vending-Bench 2$463

  The model runs a simulated vending machine business for a year on its own: finding suppliers, ordering stock, setting prices and paying the daily fees.

  54th of 60. Independent result from Epoch AI.

• SimpleQA Verified20.3%

  Short factual questions with one checked answer, asked without web search.

  71st of 78. Independent result from Epoch AI.

• FrontierMath18.3%

  Hundreds of new, unpublished math problems written by mathematicians, from hard undergraduate level up to research, with answers a computer can check.

  75th of 76. Independent result from Epoch AI.

• LMArena text1,397

  People put a question to two anonymous models and vote for the better answer.

  85th of 107. Independent result from LMArena.

• LMArena WebDev1,244

  People ask two anonymous models to build the same web page or app and vote for the better one.

  94th of 98. Independent result from LMArena.

• GPQA Diamond82.3%

  Graduate-level questions in biology, physics and chemistry, written by PhDs so that searching the web does not give the answer away.

  84th of 103. Independent result from Epoch AI.