Benchmark
MMLU-ProX
Scores are percentages. Higher is better.
- Models measured
- 27
- Scores recorded
- 36
- Sources
- 2
- IQ weight
- 2.34
Score distribution
- 73.4%
- Mean
- 79.4%
- Median
- 17.7%
- Std dev
- 59.5%
- 10th percentile
- 85.4%
- 90th percentile
- 8.1%
- Min
This benchmark has a weight of 2.34 for chat models, measured over 27 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 | Qwen3.7 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 87% |
| 2 | Qwen3.7 MaxQwen3.7-Max release · 29-language average· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 87% |
| 3 | Qwen3.7 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 85.4% |
| 4 | Qwen3.7 PlusQwen3.7-Plus release · 29-language average· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 85.4% |
| 5 | Qwen3.5 397B A17B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 84.7% |
| 6 | Qwen3.5 397B A17BQwen3.5 release/model card · 29-language average· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 84.7% |
| 7 | Qwen3.6 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 84.7% |
| 8 | Qwen3.6 PlusQwen official release table · thinking mode unless benchmark requires otherwise · 29-language average· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 84.7% |
| 9 | Nemotron 3 Ultra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 83% |
| 10 | Nemotron 3 UltraNeMo Evaluator SDK · average en/de/fr/es/it/ja/zh/hi/pt/ko· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 83% |
| 11 | Qwen3.5 122B-A10B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 82.2% |
| 12 | Qwen3.5 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 82.2% |
| 13 | Qwen 3 235B A22B Thinking 2507· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 81% |
| 14 | Qwen3.5 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 81% |
| 15 | Qwen3 VL 235Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 80.6% |
| 16 | Muse Glimmer 30B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 80.1% |
| 17 | Qwen3 235B A22B Instruct 2507· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 79.4% |
| 18 | Nemotron 3 Super 120B A12B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 79.4% |
| 19 | Nemotron 3 Super 120B A12BNeMo Evaluator / mostly NeMo Skills · average over languages· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 79.4% |
| 20 | Nemotron 3 Super 120B A12BNeMo Evaluator / mostly NeMo Skills · average over languages · report Table 8 BF16· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 79.4% |
| 21 | Qwen3 Next 80B A3Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 78.7% |
| 22 | Qwen3 VL 235B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 77.8% |
| 23 | Qwen3 VL 32B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 77.2% |
| 24 | Qwen3 Next 80B A3B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 76.7% |
| 25 | Qwen3.5 9B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 76.3% |
| 26 | qwen3-vl-30bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 76.1% |
| 27 | Qwen3 VL 32B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 73.4% |
| 28 | Qwen3.5 4B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 71.5% |
| 29 | qwen3-vl-30b· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 70.9% |
| 30 | Qwen: Qwen3 VL 8B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 70.7% |
| 31 | Qwen3 VL 8B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 65.4% |
| 32 | Nemotron 3 Nano 30B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 59.5% |
| 33 | Qwen3.5 2B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 52.3% |
| 34 | Qwen3.5 0.8B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 34.6% |
| 35 | Gemma 3n E4B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 19.9% |
| 36 | Gemma 3n E2b It· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 8.1% |
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.