Benchmark
Arena ELO Text to Image - Russian
Higher scores are better.
All image generation benchmarksScores from LMArena data.
- Models measured
- 8
- Scores recorded
- 8
- Sources
- 1
- IQ weight
- 2.07
Score distribution
- 840.8
- Mean
- 933.7
- Median
- 134.5
- Std dev
- 663.8
- 10th percentile
- 960.7
- 90th percentile
- 658.1
- Min
This benchmark has a weight of 2.07 for image-generation models, measured over 8 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 | DALL-E 3· LMArena data | 978 |
| 2 | Luma Photon· LMArena data | 960.7 |
| 3 | Recraft V3· LMArena data | 941.9 |
| 4 | Ideogram V2· LMArena data | 933.7 |
| 5 | Imagen 3· LMArena data | 904.5 |
| 6 | FLUX1.1 [pro]· LMArena data | 685.9 |
| 7 | Stable Diffusion 3.5 Large· LMArena data | 663.8 |
| 8 | FLUX.1 [dev]· LMArena data | 658.1 |
Data credits: LMArena, CC BY 4.0 (licence)