Claude Sonnet 5.5

4 runs · 4 datasets · 1 model

slug: claude-sonnet-5-5

0.771

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 raw

raw--claude-sonnet-5-5--tdefault--tplcurrent--7e6e6806

0.703 ± 0.039

SPS · 95% CI [0.664, 0.741] · n = 100

Question-type breakdown (6 topics)

Topic	SPS	p_dist	p_rank	p_refuse	N
Health & Science low n — suggestive only	1.000	1.000	1.000	1.000	1
Economy & Work low n — suggestive only	0.770	0.707	0.833	0.949	3
General Attitudes low n — suggestive only	0.684	0.713	0.654	0.969	4
Trust & Wellbeing low n — suggestive only	0.656	0.522	0.790	1.000	2
International Relations & Security	0.631	0.624	0.638	0.918	60
Politics & Governance	0.515	0.510	0.519	0.825	30

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 raw

raw--claude-sonnet-5-5--tdefault--tplcurrent--4417056f

0.642 ± 0.044

SPS · 95% CI [0.598, 0.685] · n = 75

Question-type breakdown (7 topics)

Topic	SPS	p_dist	p_rank	p_refuse	N
Social Values & Religion	0.543	0.536	0.550	0.977	14
Politics & Governance low n — suggestive only	0.536	0.523	0.549	0.975	9
Health & Science low n — suggestive only	0.517	0.533	0.500	0.967	2
Trust & Wellbeing low n — suggestive only	0.494	0.537	0.451	0.951	3
International Relations & Security	0.468	0.444	0.492	0.974	33
General Attitudes	0.450	0.434	0.465	0.960	10
Economy & Work low n — suggestive only	0.227	0.171	0.283	0.981	4

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 raw

raw--claude-sonnet-5-5--tdefault--tplcurrent--6bb7385f

0.771 ± 0.032

SPS · 95% CI [0.739, 0.804] · n = 100

Question-type breakdown (9 topics)

Topic	SPS	p_dist	p_rank	p_refuse	N
Technology & Digital Life low n — suggestive only	0.860	0.852	0.867	0.995	4
Media & Information low n — suggestive only	0.851	0.841	0.862	0.996	2
Economy & Work	0.743	0.701	0.786	0.995	21
Trust & Wellbeing low n — suggestive only	0.743	0.669	0.816	0.994	1
Social Values & Religion	0.648	0.615	0.680	0.993	15
International Relations & Security	0.634	0.620	0.649	0.994	20
General Attitudes	0.613	0.579	0.646	0.994	35
Health & Science low n — suggestive only	0.371	0.361	0.382	0.997	1
Politics & Governance low n — suggestive only	0.179	0.156	0.201	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 raw

raw--claude-sonnet-5-5--tdefault--tplcurrent--8ca87e71

0.658 ± 0.037

SPS · 95% CI [0.619, 0.694] · n = 100

Question-type breakdown (9 topics)

Topic	SPS	p_dist	p_rank	p_refuse	N
Economy & Work	0.706	0.682	0.730	0.992	13
Technology & Digital Life	0.679	0.645	0.714	0.993	16
General Attitudes	0.520	0.496	0.545	0.936	17
International Relations & Security	0.506	0.483	0.529	0.991	15
Media & Information low n — suggestive only	0.464	0.472	0.457	0.978	1
Politics & Governance low n — suggestive only	0.444	0.372	0.516	0.981	4
Health & Science low n — suggestive only	0.425	0.416	0.434	0.994	6
Social Values & Religion	0.310	0.252	0.367	0.985	27
Identity & Demographics low n — suggestive only	0.085	0.023	0.146	0.995	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