Benchmark
Vals Web Search Index
Scores are percentages.
Benchmark sourceScores from Vals AI.
- Models measured
- 5
- Scores recorded
- 5
- Sources
- 1
- IQ weight
- 0.52
Score distribution
- 43.4%
- Mean
- 43.6%
- Median
- 6.7%
- Std dev
- 35.5%
- 10th percentile
- 53.7%
- 90th percentile
- 35.5%
- Min
This benchmark has a weight of 0.52 for chat models, measured over 5 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 5.5· Vals AI | 53.7% |
| 2 | Claude Fable 5· Vals AI | 46.9% |
| 3 | GPT-5.6 Sol· Vals AI | 43.6% |
| 4 | Gemini 3.5 Flash· Vals AI | 37% |
| 5 | Grok 4.5· Vals AI | 35.5% |