Althing (Qwen 3.8 Flash)

4 runs · 4 datasets · 1 model

slug: althing-qwen-3-8-flash

0.870

Best SPS · opinionsqa

Disaggregated subgroup scorecard. Each card below is one published run for this vendor; expand the question-type and demographic-subgroup sections to see the matrix beneath the headline SPS. Where coverage permits, 95% CI bands accompany the point estimate.

What each cell measures

Each cell compares this vendor's synthetic responses against real human respondents in that demographic subgroup — published survey ground truth, not a model's guess about the subgroup. Higher = closer to how that real subgroup actually answered.

Demographic conditioning here is not stereotyping: every conditioned score is checked against what real subgroup members said, not against assumptions about them — and where the vendor's output diverges from the real subgroup, the score drops.

globalopinionqa — ground truth: Durmus et al. 2023, Anthropic — llm_global_opinions
gss — ground truth: NORC at the University of Chicago — General Social Survey
opinionsqa — ground truth: Santurkar et al., ICML 2023 — Whose Opinions Do LLMs Reflect? (derived from Pew American Trends Panel)
subpop — ground truth: Suh et al., ACL 2025 — SubPOP: Subpopulation-Level Opinion Prediction

Low-n cells: cells with n < 30 are shown muted and tagged low n — suggestive only instead of color-graded; they are reported for transparency, not as findings.

CIs: "no CI — single run" marks point estimates from a single run with no confidence interval yet; treat the uncertainty as unknown, never zero.

Columns: Score = distributional parity (p_dist) restricted to the subgroup · p_cond = conditioning strength vs the unconditioned baseline · N = questions answered under that conditioning · Cov. = coverage dot derived from N (green = high, ≥100 · amber = medium, 50–99 · red = low, <50). Topic tables: SPS = Survey Parity Score for the topic · p_dist = 1 − mean(JSD) · p_rank = (1 + mean(τ)) / 2 · p_refuse = 1 − mean(|R_model − R_human|).

Multiple comparisons: with this many subgroup cells, a few extreme cells are expected by chance alone — read patterns across a dimension, not single cells.

globalopinionqa product

althing--qwen3.8-flash--tdefault--tplcurrent--abe04fc7

0.804 ± 0.027

SPS · 95% CI [0.776, 0.830] · n = 100

Question-type breakdown (6 topics)

Topic	SPS	p_dist	p_rank	p_refuse	N
Economy & Work low n — suggestive only	0.935	0.900	0.969	0.949	3
Trust & Wellbeing low n — suggestive only	0.800	0.717	0.883	1.000	2
General Attitudes low n — suggestive only	0.764	0.834	0.693	1.000	4
International Relations & Security	0.723	0.724	0.723	0.987	60
Politics & Governance	0.678	0.713	0.643	0.961	30
Health & Science low n — suggestive only	0.488	0.976	0.000	1.000	1

Topics with N < 10 are muted and tagged "low n — suggestive only": too few questions for a stable 3-decimal score.

Not yet measured

This vendor has no demographic-conditioned runs for age, geography, education, or any other subgroup dimension on globalopinionqa. No cells are fabricated — scores appear here only when a conditioned run actually measured them.

How to submit a demographic-conditioned run →

gss product

althing--qwen3.8-flash--tdefault--tplcurrent--1b56d7bd

0.844 ± 0.023

SPS · 95% CI [0.822, 0.868] · n = 75

Question-type breakdown (7 topics)

Topic	SPS	p_dist	p_rank	p_refuse	N
Health & Science low n — suggestive only	0.830	0.872	0.787	0.967	2
International Relations & Security	0.801	0.798	0.805	0.974	33
Social Values & Religion	0.795	0.795	0.795	0.977	14
Politics & Governance low n — suggestive only	0.778	0.763	0.792	0.975	9
Economy & Work low n — suggestive only	0.771	0.737	0.806	0.981	4
General Attitudes	0.744	0.748	0.740	0.960	10
Trust & Wellbeing low n — suggestive only	0.595	0.590	0.600	0.951	3

Topics with N < 10 are muted and tagged "low n — suggestive only": too few questions for a stable 3-decimal score.

Not yet measured

This vendor has no demographic-conditioned runs for age, geography, education, or any other subgroup dimension on gss. No cells are fabricated — scores appear here only when a conditioned run actually measured them.

How to submit a demographic-conditioned run →

opinionsqa product

althing--qwen3.8-flash--tdefault--tplcurrent--a4e37b94

0.870 ± 0.015

SPS · 95% CI [0.855, 0.884] · n = 100

Question-type breakdown (9 topics)

Topic	SPS	p_dist	p_rank	p_refuse	N
Media & Information low n — suggestive only	0.940	0.921	0.959	0.996	2
Health & Science low n — suggestive only	0.903	0.849	0.956	0.997	1
Economy & Work	0.822	0.799	0.845	0.995	21
Social Values & Religion	0.821	0.785	0.856	0.993	15
Technology & Digital Life low n — suggestive only	0.820	0.804	0.837	0.995	4
International Relations & Security	0.814	0.815	0.813	0.994	20
General Attitudes	0.788	0.768	0.808	0.994	35
Trust & Wellbeing low n — suggestive only	0.743	0.669	0.816	0.994	1
Politics & Governance low n — suggestive only	0.576	0.494	0.658	0.996	1

Topics with N < 10 are muted and tagged "low n — suggestive only": too few questions for a stable 3-decimal score.

Not yet measured

This vendor has no demographic-conditioned runs for age, geography, education, or any other subgroup dimension on opinionsqa. No cells are fabricated — scores appear here only when a conditioned run actually measured them.

How to submit a demographic-conditioned run →

subpop product

althing--qwen3.8-flash--tdefault--tplcurrent--7e9168ad

0.828 ± 0.022

SPS · 95% CI [0.804, 0.849] · n = 100

Question-type breakdown (9 topics)

Topic	SPS	p_dist	p_rank	p_refuse	N
Identity & Demographics low n — suggestive only	0.889	0.944	0.833	0.995	1
Health & Science low n — suggestive only	0.855	0.874	0.837	0.994	6
Economy & Work	0.805	0.792	0.817	0.992	13
General Attitudes	0.777	0.785	0.768	0.936	17
Technology & Digital Life	0.751	0.720	0.782	0.993	16
Politics & Governance low n — suggestive only	0.740	0.715	0.765	0.983	4
International Relations & Security	0.733	0.732	0.734	0.991	15
Social Values & Religion	0.702	0.683	0.720	0.984	27
Media & Information low n — suggestive only	0.592	0.554	0.629	0.978	1

Topics with N < 10 are muted and tagged "low n — suggestive only": too few questions for a stable 3-decimal score.

Not yet measured

This vendor has no demographic-conditioned runs for age, geography, education, or any other subgroup dimension on subpop. No cells are fabricated — scores appear here only when a conditioned run actually measured them.

How to submit a demographic-conditioned run →

No demographic conditioning data has been published for this vendor yet. The question-type matrix above shows topic-level parity; subgroup rows fill in once Althing-style conditioned runs land.

← Back to leaderboard