Benchmark
Arena ELO Text Factuality - Industry Entertainment and Sports and Media
People compare model answers and choose which they prefer. Higher scores are better.
All human preference benchmarksScores from LMArena data.
- Models measured
- 150
- Scores recorded
- 169
- Sources
- 1
- IQ weight
- 2.16
Score distribution
- 1,414.5
- Mean
- 1,418.2
- Median
- 43.7
- Std dev
- 1,351.5
- 10th percentile
- 1,463.3
- 90th percentile
- 1,269.3
- Min
This benchmark has a weight of 2.16 for chat models, measured over 150 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 | Muse Glimmer· LMArena data | 1,363.2 |
| 152 | MiniMax M2.5· LMArena data | 1,351.5 |
| 153 | nova-experimental-chat10-20· LMArena data | 1,350 |
| 154 | Nemotron 3 Super 120B A12B· LMArena data | 1,349 |
| 155 | Qwen3 Next 80B A3B Instruct· LMArena data | 1,343.7 |
| 156 | Trinity Large Preview· LMArena data | 1,342.3 |
| 157 | Trinity Large Thinking· LMArena data | 1,333.4 |
| 158 | Granite 4.2 30B· LMArena data | 1,329.4 |
| 159 | Nova 2 Lite· LMArena data | 1,328 |
| 160 | GPT OSS 120B· LMArena data | 1,326.5 |
| 161 | GLM 4.7 Flash· LMArena data | 1,325.4 |
| 162 | Command A03-2025· LMArena data | 1,325.3 |
| 163 | Nemotron 3 Nano 30B A3BBF16· LMArena data | 1,321.5 |
| 164 | MiniMax M2· LMArena data | 1,319.2 |
| 165 | Nemotron 3.5 Lightning 30B A3BNVFP4· LMArena data | 1,318.6 |
| 166 | Granite 4.2 8B· LMArena data | 1,312.9 |
| 167 | Olmo 3.1 32B Instruct· LMArena data | 1,303.7 |
| 168 | Granite 4.2 3B· LMArena data | 1,278.4 |
| 169 | Olmo 3.1 32B Think· LMArena data | 1,269.3 |
Showing 151–169 of 169 results.
Data credits: LMArena, CC BY 4.0 (licence)