Benchmark
Design Arena Elo (models/svg)
People compare model answers and choose which they prefer. Higher scores are better.
- Models measured
- 100
- Scores recorded
- 112
- Sources
- 1
- IQ weight
- 1.97
Score distribution
- 1,139.3
- Mean
- 1,140
- Median
- 115.3
- Std dev
- 977
- 10th percentile
- 1,288
- 90th percentile
- 856
- Min
This benchmark has a weight of 1.97 for chat models, measured over 98 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 |
|---|---|---|
| 101 | Mistral Large 3· Design Arena Leaderboards data | 977 |
| 102 | Mistral Medium 3.1· Design Arena Leaderboards data | 977 |
| 103 | INTELLECT-3· Design Arena Leaderboards data | 976 |
| 104 | Grok 3· Design Arena Leaderboards data | 967 |
| 105 | GPT-5.1 Codex Mini· Design Arena Leaderboards data | 962 |
| 106 | DeepSeek Chat· Design Arena Leaderboards data | 961 |
| 107 | Grok 4 Fastreasoning· Design Arena Leaderboards data | 960 |
| 108 | DeepSeek V3.1· Design Arena Leaderboards data | 951 |
| 109 | Mistral Medium 3.5· Design Arena Leaderboards data | 934 |
| 110 | Grok 4.1 Fastnon-reasoning· Design Arena Leaderboards data | 928 |
| 111 | Grok 4 Fastnon-reasoning· Design Arena Leaderboards data | 923 |
| 112 | Olmo 3.1 32B Think· Design Arena Leaderboards data | 856 |
Showing 101–112 of 112 results.