Benchmark
Design Arena Elo (models/gamedev)
People compare model answers and choose which they prefer. Higher scores are better.
- Models measured
- 148
- Scores recorded
- 160
- Sources
- 1
- IQ weight
- 1.91
Score distribution
- 1,136.4
- Mean
- 1,134
- Median
- 150.8
- Std dev
- 942
- 10th percentile
- 1,317
- 90th percentile
- 745
- Min
This benchmark has a weight of 1.91 for chat models, measured over 148 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 |
|---|---|---|
| 151 | Magistral Small 2509· Design Arena Leaderboards data | 914 |
| 152 | Qwen 3 235B A22B· Design Arena Leaderboards data | 900 |
| 153 | GPT 4o· Design Arena Leaderboards data | 878 |
| 154 | Qwen3 30B A3B· Design Arena Leaderboards data | 871 |
| 155 | Mistral Large2411· Design Arena Leaderboards data | 860 |
| 156 | Mistral Small2506· Design Arena Leaderboards data | 860 |
| 157 | Llama 4 Maverick· Design Arena Leaderboards data | 810 |
| 158 | Codestral 2· Design Arena Leaderboards data | 784 |
| 159 | Devstral Small 2505· Design Arena Leaderboards data | 753 |
| 160 | Llama 4 Scout· Design Arena Leaderboards data | 745 |
Showing 151–160 of 160 results.