Benchmarks · knowledge

AA-Omniscience Humanities & Social Sciences

AA-Omniscience Index (-100..100) on the Humanities & Social Sciences questions only: right answers minus made-up ones, abstaining scores 0.

CategoryVersion

136 models · 267 results · data as of 2026-10-29 · artificialanalysis.ai ↗

All results

267 rows

#	Model	Effort	Score
1	Opus 5.5	max	44.7
2	GPT-6 Astra	max	43.1
3	GPT-6 Astra	high	41.2
4	GPT-6 Astra	xhigh	41.2
5	Fable 5.1	max	41.0
6	GPT-6 Astra	medium	40.7
7	GPT-6.1 Sol	high	40.3
8	Opus 5.5	xhigh	40.1
9	Opus 5.5	high	39.6
10	Gemini 4 Argon	high	39.6
11	GPT-6.1 Sol	max	39.1
12	GPT-6 Astra	low	38.9
13	GPT-6.1 Sol	medium	38.8
14	Fable 5.1	high	38.6
15	Fable 5.1	medium	38.5
16	GPT-6.1 Sol	xhigh	38.5
17	Fable 5.1	xhigh	38.4
18	Opus 5.5	medium	37.7
19	Opus 5.5	low	36.5
20	GPT-6.1 Sol	low	36.1
21	Opus 5	max	35.3
22	Fable 5.1	low	34.4
23	Opus 5	xhigh	33.7
24	Grok 4.7	low	31.5
25	Gemini 3.8 Flash	high	31.2
26	Grok 4.7	high	31.1
27	Sonnet 5.5	max	30.8
28	GPT-6.1 Terra	max	30.8
29	Grok 4.6	high	30.5
30	Muse Spark 1.1	xhigh	30.1