Benchmark
WMT24++
Multilingual benchmarks compare model performance across languages. Scores are percentages. Higher is better.
- Models measured
- 22
- Scores recorded
- 28
- Sources
- 2
- IQ weight
- 1.55
Score distribution
- 70.6%
- Mean
- 78.9%
- Median
- 17.8%
- Std dev
- 45.8%
- 10th percentile
- 85.8%
- 90th percentile
- 27.2%
- Min
This benchmark has a weight of 1.55 for chat models, measured over 22 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 | Nemotron 3 Super 120B A12B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 86.7% |
| 2 | Nemotron 3 Super 120B A12BNeMo Evaluator / mostly NeMo Skills · en→xx· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 86.7% |
| 3 | Nemotron 3 Nano 30B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 86.2% |
| 4 | Qwen3.7 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 85.8% |
| 5 | Qwen3.7 MaxQwen3.7-Max release · 55-language average · XCOMET-XXL· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 85.8% |
| 6 | Qwen3.7 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 84.6% |
| 7 | Qwen3.7 PlusQwen3.7-Plus release · 55-language average · XCOMET-XXL· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 84.6% |
| 8 | Qwen3.6 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 84.3% |
| 9 | Qwen3.6 PlusQwen official release table · thinking mode unless benchmark requires otherwise · 55-language XCOMET-XXL average· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 84.3% |
| 10 | Nemotron 3 Ultra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 83.7% |
| 11 | Nemotron 3 UltraNeMo Evaluator SDK · en→xx· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 83.7% |
| 12 | Command A Plus 05 2026· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 81% |
| 13 | Qwen3.5 397B A17B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 78.9% |
| 14 | Qwen3.5 397B A17BQwen3.5 release/model card · 55-language average · XCOMET-XXL· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 78.9% |
| 15 | Qwen3.5 122B-A10B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 78.3% |
| 16 | Qwen3 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 77.6% |
| 17 | Qwen3.5 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 77.6% |
| 18 | Qwen3.5 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 76.3% |
| 19 | Qwen3.5 9B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 72.6% |
| 20 | Qwen3.5 4B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 66.6% |
| 21 | Gemma 3 27B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 53.4% |
| 22 | Gemma 3 12B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 51.6% |
| 23 | Gemma 3n E4B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 50.1% |
| 24 | Gemma 3 4B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 46.8% |
| 25 | Qwen3.5 2B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 45.8% |
| 26 | Gemma 3n E2b It· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 42.7% |
| 27 | Gemma 3 1b it· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 35.9% |
| 28 | Qwen3.5 0.8B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 27.2% |
Data credits: Data by LLM Stats · BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.