Llama 3.3 70B, raw
OpinionsQA · Raw LLM · default settings · 5 questions
raw--llama-3.3-70b-instruct--tdefault--tplcurrent--bc0674a7
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
12
± 21.1
SPS
SPS, 0 to 1
0.791
± 0.050
Distribution gap
mean JSD, lower is better
0.292
± 0.023
Rank agreement
Kendall τ, −1 to 1
0.580
± 0.006
Variance summary
- Replicates
- 2
- Std dev
- 21.1 Index points (SPS 0.050)
- Range
- Index -3 to 27 (SPS 0.756–0.827)
- Coefficient of variation (SPS)
- 0.0631
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 (2)
| Run | Timestamp | Index | SPS | JSD | Kendall τ | N |
|---|---|---|---|---|---|---|
| opinionsqa_openrouter_meta-llama_llama-3.3-70b-instruct_20260410_181833 | 2026-04-10 18:18 UTC | -3 | 0.756 | 0.275 | 0.575 | 50 |
| opinionsqa_openrouter_meta-llama_llama-3.3-70b-instruct_20260410_200818 | 2026-04-10 20:08 UTC | 27 | 0.827 | 0.308 | 0.584 | 5 |