Model rankings

Rank	Change	Model	Score	95% interval
1	—	Realtime TTS 1.5 MaxClosedInworld	1,208	±18
2	—	Gemini 3.1 Flash TTSClosedGoogle	1,206	±17
3	—	StepAudio 2.5 TTSClosedStepFun	1,187	±26
4	—	Eleven v3ClosedElevenLabs	1,178	±12
5	—	Inworld TTS 1 MaxClosedInworld	1,164	±17
6	—	Speech 2.8 HDClosedMiniMax	1,163	±12
7	—	SIMBA 3.0ClosedSpeechify	1,159	±36
8	—	Realtime TTS 1.5 MiniClosedInworld	1,158	±15
9	—	Step TTS 2 (Mar 2026)ClosedStepFun	1,148	±19
10	—	Speech 2.8 TurboClosedMiniMax	1,146	±11
11	—	Speech 2.6 HDClosedMiniMax	1,133	±12
12	—	Speech 2.6 TurboClosedMiniMax	1,129	±11
13	—	Fish Audio S2 ProOpenFish Audio	1,128	±21
14	—	Azure HD 2.5ClosedMicrosoft	1,120	±21
15	—	Speech-02-HDClosedMiniMax	1,117	±11
16	—	Inworld TTS 1ClosedInworld	1,116	±16
17	—	Multilingual v2ClosedElevenLabs	1,107	±8
18	—	Step Audio EditX (Mar 2026)OpenStepFun	1,104	±21
19	—	TTS-1ClosedOpenAI	1,101	±8
20	—	Turbo v2.5ClosedElevenLabs	1,098	±8
21	—	TTS-1 HDClosedOpenAI	1,097	±12
22	—	Speech-02-TurboClosedMiniMax	1,096	±11
23	—	MiMo-V2.5-TTSClosedXiaomi	1,089	±36
24	—	Flash v2.5ClosedElevenLabs	1,087	±9
25	—	Gemini 2.5 Flash Lite TTSClosedGoogle	1,080	±14
26	—	Sonic 3ClosedCartesia	1,069	±13
27	—	Gradium TTSClosedGradium	1,066	±33
28	—	Magpie-Multilingual 357M (Feb 2026)OpenNVIDIA	1,063	±21
29	—	OpenAudio S1ClosedFish Audio	1,063	±10
30	—	StudioClosedGoogle	1,062	±10
31	—	SIMBA 1.6ClosedSpeechify	1,060	±19
32	—	T2A-01-HDClosedMiniMax	1,057	±10
33	—	Polly GenerativeClosedAmazon	1,056	±11
34	—	Kokoro 82M v1.0OpenKokoro	1,056	±9
35	—	Voxtral TTSOpenMistral	1,056	±21
36	—	AsyncFlow V2, asyncClosedAsync	1,052	±11
37	—	Maya1OpenMaya Research	1,050	±13
38	—	Azure NeuralClosedMicrosoft	1,048	±8
39	—	Sonic English (Oct 2024)ClosedCartesia	1,047	±12
40	—	Polly Long-FormClosedAmazon	1,044	±19
41	—	Octave 2ClosedHume AI	1,042	±13
42	—	Chirp 3: HDClosedGoogle	1,040	±12
43	—	Chatterbox HDClosedResemble AI	1,035	±10
44	—	JourneyClosedGoogle	1,033	±18
45	—	Lightning v3.1ClosedSmallest.ai	1,033	±20
46	—	Gemini 2.5 Flash TTS (Dec 2025)ClosedGoogle	1,029	±15
47	—	SIMBA 1.0ClosedSpeechify	1,026	±10
48	—	MAI-Voice-1ClosedMicrosoft	1,023	±20
49	—	Gemini 2.5 Pro (Dec 2025)ClosedGoogle	1,023	±16
50	—	Octave TTSClosedHume AI	1,018	±10
51	—	T2A-01-TurboClosedMiniMax	1,018	±9
52	—	MiMo-V2-TTSClosedXiaomi	1,011	±20
53	—	Fish Speech 1.5OpenFish Audio	1,011	±10
54	—	ChatterboxOpenResemble AI	1,006	±10
55	—	Magpie-Multilingual 357MOpenNVIDIA	1,002	±11
56	—	Arcana v3ClosedRime	1,001	±20
57	—	Zonos-v0.1OpenZyphra	1,000	±0
58	—	LMNTClosedLMNT	966	±11
59	—	VibeVoice 7BOpenMicrosoft	960	±17
60	—	VibeVoice 1.5BClosedMicrosoft	958	±15
61	—	Murf Speech Gen 2ClosedMurf AI	956	±9
62	—	OpenVoice v2OpenOpenVoice	949	±8
63	—	Magpie MultilingualClosedNVIDIA	947	±18
64	—	Neuphonic TTSClosedNeuphonic	941	±18
65	—	Qwen3 TTSClosedAlibaba	930	±15
66	—	Qwen3 TTS FlashClosedAlibaba	930	±17
67	—	Mist V2ClosedRime	892	±14
68	—	XTTS v2OpenCoqui	886	±9
69	—	StyleTTS 2OpenStyleTTS	879	±9
70	—	WaveNetClosedGoogle	873	±8
71	—	Polly NeuralClosedAmazon	868	±16
72	—	Neural2ClosedGoogle	844	±8
73	—	StandardClosedGoogle	844	±8
74	—	Falcon (Beta)ClosedMurf AI	814	±18
75	—	Polly StandardClosedAmazon	799	±12
76	—	MetaVoice v1OpenMetaVoice	764	±14

26 more models

Intelligence over time

Each maker's best model at the time on the Artificial Analysis Intelligence Index, by the month it was released.

Gained most · Anthropic +57.2Highest now · Anthropic 64.6Gap between highest and lowest 18.1 ptsTime range Nov 2025 – Nov 2026

64.6Anthropic60.0Google56.9OpenAI50.1Meta46.5Kimi