Artificial Analysis Legal Index

Artificial Analysis · 50 models

Rank	Model	Score
1	Gemini 4 Carbon (High)	62
2	Gemini 4 Carbon (Medium)	59.5
3	Claude Opus 5.5 (Max, Default Fallback)	58
4	GPT-6 Astra (Xhigh)	55.7
5	GPT-6 Astra (Max)	55.6
6	GPT-6 Astra (High)	55.1
7	Claude Opus 5.5 (Xhigh, Default Fallback)	54.7
8	Gemini 4 Argon (High)	54.6
9	Claude Fable 5.1 (Max, Default Fallback)	54.5
10	Gemini 4 Carbon (Low)	54
11	Claude Fable 5.1 (Xhigh, Default Fallback)	53.7
11	GPT-6.1 Sol (Max)	53.7
11	GPT-6.1 Sol (Xhigh)	53.7
14	Claude Sonnet 5.5 (Max, Default Fallback)	52.2
15	Claude Opus 5.5 (High, Default Fallback)	52
16	GPT-6 Astra (Medium)	51.8
16	GPT-6.1 Sol (High)	51.8
18	Muse Wonder Full (Max)	50.7
19	Claude Fable 5.1 (High, Default Fallback)	49.8
20	Claude Opus 5.5 (Medium, Default Fallback)	49.7
21	Kimi K3.1 Pro	49.2
22	GPT-6.1 Sol (Medium)	49
23	Claude Fable 5.1 (Medium, Default Fallback)	48.1
24	GPT-6 Astra (Low)	47.7
25	Claude Sonnet 5.5 (Xhigh, Default Fallback)	47.4
26	Grok 4.7 (Xhigh)	47.2
27	Muse Wonder (Max)	46.9
28	Claude Fable 5.1 (Low, Default Fallback)	46.7
29	Grok 4.7 (High)	46.6
30	GPT-6.1 Terra (Max)	46.4
31	Muse Spark 1.3 (Max)	45.2
32	Grok 4.7 (Low)	44.4
33	Claude Sonnet 5.5 (High, Default Fallback)	44.1
34	GPT-6.1 Terra (Xhigh)	43.8
35	Claude Opus 5.5 (Low, Default Fallback)	43.5
36	Muse Spark 1.3 (Xhigh)	43.2
37	GPT-6.1 Sol (Low)	42.9
38	GPT-6.1 Terra (High)	42.5
39	Gemini 3.8 Flash (High)	41.7
40	Gemini 3.8 Flash (Medium)	41.6
41	Qwen3.8 Max (0902)	41
42	GPT-6.1 Terra (Medium)	40.5
43	Muse Spark Open (Xhigh)	39.6
44	Claude Sonnet 5.5 (Medium, Default Fallback)	38.8
45	Claude Haiku 5.5 (Max)	38.7
46	Step 5 Preview	38.6
47	DeepSeek V4.1 Flash 1017 (Max)	37.7
48	GPT-6.1 Terra (Low)	37.3
49	Claude Haiku 5.5 (Xhigh)	37.1
50	Qwen3.8 2.4T A95B	37