Benchmark
Vals Immigration
Scores are percentages.
Benchmark sourceScores from Vals AI.
- Models measured
- 25
- Scores recorded
- 25
- Sources
- 1
- IQ weight
- 2.49
Score distribution
- 66.6%
- Mean
- 67.5%
- Median
- 4.5%
- Std dev
- 61.7%
- 10th percentile
- 72.1%
- 90th percentile
- 55.7%
- Min
This benchmark has a weight of 2.49 for chat models, measured over 25 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 Fable 5.1· Vals AI | 75.4% |
| 2 | Claude Fable 5.2· Vals AI | 74% |
| 3 | Claude Opus 5.5· Vals AI | 72.1% |
| 4 | Muse Wonder Full· Vals AI | 71.2% |
| 5 | Qwen3.8 Max· Vals AI | 70.1% |
| 6 | Muse Wonder· Vals AI | 69.6% |
| 7 | Claude Sonnet 5.5· Vals AI | 69% |
| 8 | Kimi K3· Vals AI | 68.3% |
| 9 | Gemini 4 Argon· Vals AI | 68.1% |
| 10 | Grok 4.7· Vals AI | 68% |
| 11 | GPT-6.1 Sol· Vals AI | 67.8% |
| 12 | GPT-6 Astra· Vals AI | 67.7% |
| 13 | MiMo V2.6 Pro· Vals AI | 67.5% |
| 14 | GLM 5.3· Vals AI | 66.7% |
| 15 | Muse Spark 1.2· Vals AI | 66.5% |
| 16 | Grok 4.6· Vals AI | 66% |
| 17 | DeepSeek V4.1 Flash· Vals AI | 65.6% |
| 18 | Muse Spark 1.3· Vals AI | 65% |
| 19 | Mistral Large 4· Vals AI | 63.7% |
| 20 | Gemini 3.8 Flash· Vals AI | 63.4% |
| 21 | GPT-6 Luna· Vals AI | 62.5% |
| 22 | Claude Haiku 5.5· Vals AI | 61.8% |
| 23 | DeepSeek V4 Pro 0813· Vals AI | 61.7% |
| 24 | MiniMax M3· Vals AI | 57.5% |
| 25 | Gemini 3.5 Flash Lite· Vals AI | 55.7% |