This New AI Music Model Is Already Better Than Suno—We Put ACE to the Test

In brief ACE Music v1 ranks ahead of Suno v6 in Artificial Analysis' blind listening benchmark for AI-generated vocal music. Decrypt's tests found stronger melodies, more natural voices and cleaner endings, but Suno handled some niche genres better. The flagship model remains proprietary, while ACE-Step 1.5 is already open source and ACE Music v1 Flash is scheduled for release later in 2026. Artificial intelligence has gotten pretty good at writing songs. Now, a relatively unfamiliar competitor has managed to beat Suno, arguably the biggest name in AI music, at its own game.ACE Music v1, developed by ACE Studio, has taken first place on Artificial Analysis' vocal music leaderboard, scoring 1,160 Elo points against Suno v6's 1,144.The AA-Music-Vocal v1.1 benchmark measures the quality of AI-generated songs containing vocals. Evaluators listen to tracks produced from identical prompts without knowing which model created them, then choose their favorite. Those preferences determine an Elo-style rating, with higher scores indicating stronger listener preference.The lead is relatively narrow, and the models' statistical confidence intervals overlap. Suno also retains the top position on the separate instrumental music leaderboard.ACE Studio, founded in 2018, originally focused on synthesizing singing voices from MIDI notes and lyrics. Its latest ACE Music v1 model generates complete songs from written descriptions or user-provided lyrics.We tested it. And it's genuinely good.In Decrypt's hands-on tests, ACE Music consistently produced more melodic and coherent songs in mainstream styles.That said, the vocal performances sounded more natural in general, with fewer of the synthetic artifacts that sometimes make AI singers sound like they're struggling to pronounce their own lyrics, use a lot of autotune or hallucinate words just to fill spaces. (Go ahead and give our song a listen here, which incidentally is about our latest company announcement regarding the Information Exchange.)ACE also handled song endings better. Where Suno occasionally introduces strange sounds, unnecessary repetitions, hallucinations or abrupt musical changes near the finish, ACE generally maintained its structure and delivered cleaner conclusions.That matters because making a convincing chorus is relatively easy compared with maintaining a musical idea throughout an entire composition even if the lyrics are already over.Suno still had an advantage when we pushed the models toward less conventional genres.In our melodic death metal test, ACE consistently produced tracks featuring a woman singing clearly in a pleasant, clean voice, missing the aggressive vocal delivery expected from the requested style. In general it confuses metal genres all over. Suno offered more creative arrangements in the proper heavy styles, with better stylistic consistency in several similarly demanding prompts.The results were subjective rather than a controlled benchmark, but they showed why a leaderboard victory doesn't automatically make one model better for every musician.More than a song generatorACE's most interesting feature may be its songwriting workflow.Its “Idea” feature can develop a basic concept into lyrics and a structured composition, identifying individual song sections and describing how they should be arranged. Users can then refine the material rather than repeatedly generating completely new tracks.The v1.1 Preview goes further, creating a musical score before generating audio.“Each generation is a new performance, so the sound may differ even when the score stays the same,” the developers explain.Users can edit melodies and chords, regenerate performances, export MIDI files and separate vocals from instruments for further production.That workflow puts ACE closer to a music production assistant than a simple prompt-to-song application.Open-source ambitionsThe flagship ACE Music v1 model remains closed-source with no public API, so users can only generate via the official site. However, its developers are pursuing a parallel open-source strategy.ACE Studio and StepFun have already released ACE-Step 1.5, a separate family of models whose code and weights are publicly available. Unlike the proprietary flagship, these can run on users' own hardware—but using a weaker model.The company also promises another release.“We plan to open-source ACE Music v1 Flash in late 2026,” the developers state on their website, describing a version designed to balance quality, generation speed and hardware requirements.ACE Music is available through its browser application, with a limited free tier and paid subscriptions. Commercial usage rights for flagship-model songs require a paid plan, while ACE-Step offers a separate free generation option.For now, ACE Music v1 holds a 16-point Elo lead over Suno v6 in vocal generation. Its promised Flash release would give local users another model to try before the end of 2026.Daily Debrief NewsletterStart every day with the top news stories right now, plus original features, a podcast, videos and more. Join 72,000+ readersCreate an account to save your articles.