Claude Haiku 4.5, raw
OpinionsQA · Raw LLM · default settings · 30 questions
raw--claude-haiku-4-5--tdefault--tplcurrent--500fac40
Failed to load configuration data.
Aggregated metrics
Mean across replicates, ± sample standard deviation (shown only with 2+ replicates). SynthBench Index: 0 = random answers, 100 = real people. SPS is the raw 0 to 1 score it is computed from. Index = 100 × (SPS − SPS of random answers) ÷ (human ceiling − SPS of random answers), on this config's dataset. The leaderboard averages it over the core datasets.
Index
0 = random answers, 100 = real people
19
± 19.9
SPS
SPS, 0 to 1
0.808
± 0.047
Distribution gap
mean JSD, lower is better
0.288
± 0.011
Rank agreement
Kendall τ, −1 to 1
0.544
± 0.021
Variance summary
- Replicates
- 5
- Std dev
- 19.9 Index points (SPS 0.047)
- Range
- Index -16 to 29 (SPS 0.724–0.831)
- Coefficient of variation (SPS)
- 0.0583
Per-topic breakdown
Index per topic (mean across replicates; 0 = random answers, 100 = real people). All seven topics are shown; topics this config's questions don't cover are marked "no questions".
Show data table
Loading data…
Replicates (5)
| Run | Timestamp | Index | SPS | JSD | Kendall τ | N |
|---|---|---|---|---|---|---|
| opinionsqa_raw-anthropic_claude-haiku-4-5-20251001_20260410_161405 | 2026-04-10 16:14 UTC | -16 | 0.724 | 0.308 | 0.511 | 100 |
| opinionsqa_openrouter_anthropic_claude-haiku-4-5_20260410_201951 | 2026-04-10 20:19 UTC | 27 | 0.827 | 0.283 | 0.540 | 30 |
| opinionsqa_openrouter_anthropic_claude-haiku-4-5_20260410_202110 | 2026-04-10 20:21 UTC | 28 | 0.828 | 0.287 | 0.554 | 30 |
| opinionsqa_openrouter_anthropic_claude-haiku-4-5_20260410_210627 | 2026-04-10 21:06 UTC | 29 | 0.831 | 0.285 | 0.568 | 30 |
| opinionsqa_openrouter_anthropic_claude-haiku-4-5_20260410_210745 | 2026-04-10 21:07 UTC | 28 | 0.830 | 0.279 | 0.548 | 30 |