Benchmark
Artificial Analysis Multilingual Index
Multilingual benchmarks compare model performance across languages. Scores are index points out of 100.
All multilingual benchmarksScores from OpenRouter data docs.
- Models measured
- 55
- Scores recorded
- 55
- Sources
- 1
- IQ weight
- 2.27
Score distribution
- 0.812
- Mean
- 0.838
- Median
- 0.107
- Std dev
- 0.683
- 10th percentile
- 0.906
- 90th percentile
- 0.351
- Min
This benchmark has a weight of 2.27 for chat models, measured over 55 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 |
|---|---|---|
| 51 | Ministral 8B2512· OpenRouter data docs | 0.663 |
| 52 | Nemotron 3 Nano 30B A3B· OpenRouter data docs | 0.612 |
| 53 | Ministral 3B2512· OpenRouter data docs | 0.567 |
| 54 | Gemma 3 4B IT· OpenRouter data docs | 0.544 |
| 55 | Llama 3.1 8B Instruct· OpenRouter data docs | 0.351 |
Showing 51–55 of 55 results.