Quality: the BenchLeader Index

Composite of every quality benchmark, normalised per benchmark and averaged per category. Requires results on at least five benchmarks across two categories.

610 models · data as of 9 Sept 2026

1. 1GPT-6 Astra70.6
2. 2Claude Fable 570.4
3. 3Claude Fable 5.170.3
4. 4Claude Fable 5.170.2
5. 5Claude Opus 570.0
6. 6Claude Fable 5.170.0
7. 7GPT-6 Astra69.9
8. 8Claude Fable 5.169.7
9. 9GPT-6 Astra69.5
10. 10Claude Opus 569.3
11. 11GPT-6 Astra68.6
12. 12GPT-5.6 Sol68.0
13. 13Claude Fable 5.168.0
14. 14GPT-5.6 Sol67.5
15. 15GPT-6 Astra67.4

SearchAll providers01.AIAI21 LabsAlibabaAllen Institute for AIAllenaiAmazonAnt GroupAnt-groupAnthropicArcee AIBaiduByteDanceChina MobileCohereDeepSeekGoogleIBMInceptionInclusionAIKorea TelecomKwaiKATLG AI ResearchLiquid AILongCatMBZUAI Institute of Foundation ModelsMetaMicrosoftMiniMaxMistral AIMoonshot AIMotif TechnologiesMultiverse ComputingNanbeigeNaverNous ResearchNVIDIAOpenAIOpenBMBPoolsidePrime IntellectQwenRekaReka AISarvamStepFunSwiss AI InitiativeThinking MachinesTII UAETrillion LabsUnknownUpstagexAIXiaomiZhipu AIOpen weights610 of 610

#	Model	Index ↓	Provider ↕
1	GPT-6 AstraOpenAI	70.6	–
2	Claude Fable 5Anthropic	70.4	–
3	Claude Fable 5.1Anthropic	70.3	–
4	Claude Fable 5.1Anthropic	70.2	–
5	Claude Opus 5Anthropic	70.0	–
6	Claude Fable 5.1Anthropic	70.0	–
7	GPT-6 AstraOpenAI	69.9	–
8	Claude Fable 5.1Anthropic	69.7	–
9	GPT-6 AstraOpenAI	69.5	–
10	Claude Opus 5Anthropic	69.3	–
11	GPT-6 AstraOpenAI	68.6	–
12	GPT-5.6 SolOpenAI	68.0	–
13	Claude Fable 5.1Anthropic	68.0	–
14	GPT-5.6 SolOpenAI	67.5	–
15	GPT-6 AstraOpenAI	67.4	–
16	Claude Opus 5Anthropic	66.8	–
17	GPT-5.5OpenAI	66.6	–
18	Kimi K3Moonshot AIopen	66.5	–
19	GPT-5.5OpenAI	66.3	–
20	Claude Opus 5Anthropic	66.3	–
21	GPT-5.6 SolOpenAI	66.0	–
22	Claude Fable 5.1Anthropic	65.9	–
23	Claude Fable 5Anthropic	65.8	–
24	GPT-6 AstraOpenAI	65.8	–
25	Claude Opus 4.7Anthropic	65.5	–
26	GPT-5.6 SolOpenAI	65.5	–
27	Muse SparkMeta	65.4	–
28	GPT-5.6 SolOpenAI	65.3	–
29	Muse Spark 1.1Meta	64.9	–
30	GPT-5.5OpenAI	64.9	–
31	Claude Opus 4.8Anthropic	64.7	–
32	GPT-5.6 SolOpenAI	64.6	–
33	GPT-6 AstraOpenAI	64.4	–
34	Gemini 3.7 FlashGoogle	64.4	–
35	GPT-5.6 TerraOpenAI	64.2	–
36	GPT-5.4 ProOpenAI	64.2	–
37	Gemini 3.1 ProGoogle	63.9	–
38	Qwen3 8Alibaba	63.9	–
39	Gemini 3.5 FlashGoogle	63.9	–
40	Claude Fable 5Anthropic	63.9	–
41	Muse Spark 1.3Meta	63.9	–
42	Grok 4.6xAI	63.8	–
43	GPT-5.5OpenAI	63.7	–
44	Grok 4.6xAI	63.6	–
45	Gemini 3.8 FlashGoogle	63.5	–
46	GPT-5.4OpenAI	63.4	–
47	Grok 4.5xAI	63.4	–
48	Claude Opus 4.6Anthropic	63.1	–
49	GPT-5.6 TerraOpenAI	63.1	–
50	Claude Opus 5Anthropic	63.1	–
51	Kimi K3Moonshot AIopen	62.7	–
52	Muse Spark 1.2Meta	62.6	–
53	Gemini 3.7 FlashGoogle	62.5	–
54	GPT-5.3 CodexOpenAI	62.4	–
55	Gemini 3.8 FlashGoogle	62.4	–
56	Grok 4.6xAI	62.3	–
57	GPT-5.5OpenAI	62.3	–
58	GPT-5.6 TerraOpenAI	62.3	–
59	Claude Opus 4.6Anthropic	62.3	–
60	Qwen3 6Alibaba	62.0	–

Show 100 more