Benchmarks · knowledge

AA-Omniscience v1.1 Business

AA-Omniscience v1.1 Index (-100..100) on the Business questions only: right answers minus made-up ones, abstaining scores 0.

CategoryVersion

28 models · 76 results · data as of 2026-10-29 · artificialanalysis.ai ↗

All results

76 rows

#	Model	Effort	Score
1	Gemini 4 Carbon	high	42.7
2	GPT-6 Astra	high	40.7
3	GPT-6.1 Sol	max	40.0
4	GPT-6.1 Sol	xhigh	39.8
5	GPT-6 Astra	xhigh	39.6
6	GPT-6 Astra	medium	39.3
7	Fable 5.1	max	37.8
8	GPT-6.1 Sol	medium	37.6
9	GPT-6 Astra	max	37.1
10	GPT-6.1 Sol	high	36.7
11	GPT-6.1 Sol	low	35.8
12	Gemini 4 Argon	high	35.3
13	GPT-6 Astra	low	34.7
14	Fable 5.1	xhigh	34.4
15	Fable 5.1	low	31.3
16	Opus 5.5	max	30.7
17	Grok 4.7	xhigh	30.2
18	Fable 5.1	high	28.9
19	Opus 5.5	high	26.9
20	GPT-6.1 Terra	xhigh	26.7
21	Grok 4.7	high	26.7
22	Opus 5.5	medium	26.2
23	Opus 5.5	xhigh	26.2
24	Fable 5.1	medium	25.6
25	GPT-6.1 Terra	max	25.6
26	GPT-6.1 Terra	high	24.0
27	Gemini 3.8 Flash	medium	23.6
28	Opus 5.5	low	22.9
29	Grok 4.7	low	22.7
30	GPT-6.1 Terra	medium	22.0