τ³-Banking

Artificial Analysis · 50 models

Rank	Model	Score
1	Qwen3.8 Max	0.5134
2	Grok 4.6 (High)	0.5072
3	Muse Spark 1.3 (Max)	0.5052
4	GLM-5.3 (Max)	0.5031
5	Qwen3.8 2.4T A95B	0.4907
6	Qwen3.8 27B (Xhigh)	0.4804
7	Qwen3.8 Max (0902)	0.4784
8	Qwen3.8 27B (Medium)	0.4742
9	Claude Fable 5.1 (Max, Default Fallback)	0.4722
9	GLM-5.3-Flash	0.4722
9	Muse Spark 1.3 (Xhigh)	0.4722
12	Kimi K3 (Max)	0.4598
13	Claude Fable 5.1 (Xhigh, Default Fallback)	0.4577
13	Gemini 3.8 Flash (Medium)	0.4577
15	Qwen3.8-Flash-Next	0.4536
16	Gemini 3.8 Flash (High)	0.4495
17	Claude Opus 5 (High)	0.4474
18	GPT-5.6 Sol (Max)	0.4433
18	Grok 4.6 (Medium)	0.4433
20	Claude Opus 5 (Xhigh)	0.433
20	Grok 4.6 (Xhigh)	0.433
22	Claude Fable 5.1 (High, Default Fallback)	0.4309
22	GPT-6 Astra (Xhigh)	0.4309
24	Claude Opus 5 (Max)	0.4206
24	Grok 4.5 (High)	0.4206
26	Kimi K3 (Low)	0.4165
27	GPT-6 Astra (Max)	0.4144
28	Claude Fable 5.1 (Medium, Default Fallback)	0.4103
28	DeepSeek V4 Flash Vision (Max)	0.4103
30	GPT-5.6 Terra (Max)	0.4021
31	GPT-6 Astra (High)	0.4
32	DeepSeek V4 Pro 0813 (Max)	0.3959
32	GPT-5.4 (Xhigh)	0.3959
34	DeepSeek V4 Flash 0731 (Max)	0.3938
35	Claude Fable 5.1 (Low, Default Fallback)	0.3897
35	GPT-5.5 (Xhigh)	0.3897
37	Claude Opus 5 (Medium)	0.3856
37	Ling-3.0-flash-Fin	0.3856
39	Claude Fable 5 (Max, Opus 4.8 Fallback)	0.3814
39	GPT-5.6 Sol (Xhigh)	0.3814
39	Grok 4.6 (Low)	0.3814
42	Claude Sonnet 5 (Max)	0.3732
43	GPT-5.5 (High)	0.367
43	GPT-5.6 Sol (High)	0.367
45	GPT-5.6 Sol (Medium)	0.3649
46	Agnes 2.5 Pro Beta	0.3567
47	GPT-6 Astra (Medium)	0.3546
47	Gemini 3.7 Flash (Medium)	0.3546
49	Motif 3	0.3526
50	Muse Spark 1.2 (Xhigh)	0.3485