Benchmark
MMLU-Pro
Scores are percentages. Higher is better.
- Models and systems measured
- 299
- Scores recorded
- 328
- Sources
- 5
- IQ weight
- 1.01
Score distribution
- 54.6%
- Mean
- 55.3%
- Median
- 26.8%
- Std dev
- 17.2%
- 10th percentile
- 85.2%
- 90th percentile
- 0.649%
- Min
This benchmark has a weight of 1.01 for chat models, measured over 292 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model or system | Score |
|---|---|---|
| 101 | Claude 3.5 Sonnet· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 76.1% |
| 102 | Phi 4 Reasoning Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 76% |
| 103 | Gemini 1.5 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 75.8% |
| 104 | MiniMax Text 01· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 75.7% |
| 105 | Grok 2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 75.5% |
| 106 | Trinity Large PreviewTrinity technical report · Table 4 · exact reported precision· Reported by Arcee AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 75.3% |
| 107 | Trinity Large Preview· OpenEvals Leaderboard data· Reported by the model's developer. The source relaying it did not verify it. | 75.2% |
| 108 | Trinity Large PreviewTrinity-Large-Preview Model Card · rounded to one decimal· Reported by Arcee AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 75.2% |
| 109 | GPT 4o· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 74.7% |
| 110 | Llama 4 Scout· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 74.3% |
| 111 | Llama 4 Scout0-shot· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 74.3% |
| 112 | Phi-4-reasoning· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 74.3% |
| 113 | Granite 4.2 8B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 74% |
| 114 | Qwen3-4B-Thinking-2507· OpenEvals Leaderboard data· Reported by the model's developer. The source relaying it did not verify it. | 74% |
| 115 | GPT OSS 20b· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 73.6% |
| 116 | Llama 3.1 405B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 73.3% |
| 117 | Grok 2 mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 72% |
| 118 | Gemini 2.0 Flash Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 71.6% |
| 119 | Qwen3 VL 8B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 71.6% |
| 120 | Qwen2.5 72B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 71.6% |
| 121 | Qwen2.5 72B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 71.1% |
| 122 | MiniCPM5-2B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 70.8% |
| 123 | Phi 4· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 3 sources
| 70.4% |
| 124 | Qwen3 4B Instruct 2507· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 69.6% |
| 125 | ERNIE-4.5-300B-A47B-Base-PT· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 69.5% |
| 126 | Gemma 4 E4B-it· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 69.4% |
| 127 | Qwen2.5 32B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 69.2% |
| 128 | Mistral Small 3.2 24B Instruct2506· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 69.1% |
| 129 | Qwen2.5 32B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 69% |
| 130 | Llama 3.3 70B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 68.9% |
| 131 | Claude 3 Opus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 68.5% |
| 132 | MiMo V2.5 Pro· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 68.5% |
| 133 | Qwen 3 235B A22B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 68.2% |
| 134 | Mistral Large Instruct 2411· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 67.9% |
| 135 | Granite 4.2 3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 67.8% |
| 136 | Gemma 3 27B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 67.5% |
| 137 | Gemini 1.5 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 67.3% |
| 138 | Hunyuan A13B Instruct· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 67.3% |
| 139 | Mistral Small 3.1 24b Instruct 2503· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 66.8% |
| 140 | Qwen3.5 2B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 66.5% |
| 141 | Llama 3.1 70B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 66.4% |
| 142 | Llama 3.1 70B Instruct5-shot · chain of thought· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 66.4% |
| 143 | Mistral Small 24B Instruct2501· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 66.3% |
| 144 | Mistral-Large-Instruct-2407· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 65.9% |
| 145 | DeepSeek V2.5· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 65.8% |
| 146 | Claude Haiku 3.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 65% |
| 147 | Qwen2 72B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 64.4% |
| 148 | Qwen 2.5 14B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 63.7% |
| 149 | Qwen2.5 14B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 63.7% |
| 150 | Qwen3 30B A3b Base· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 61.7% |
Showing 101–150 of 322 results.
Not ranked
The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.
| Model or system | Score |
|---|---|
| DeepSeek V4.1 Flash BaseEM · 5-shot· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 74.1% |
| MiMo V2 Flash Baseofficial Base table · 5-shot· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 73.2% |
| Qwen3.5-397B-A17B-BaseQwen3.5 release/model card · base-model table· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 76% |
| Qwen3.7-Plus-BaseQwen3.8-Flash-Next release/model card · base-model table· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 70.9% |
| Qwen3.8-27B-BaseQwen3.8-Flash-Next release/model card · base-model table· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 68.6% |
| Qwen3.8-Flash-Next-BaseQwen3.8-Flash-Next release/model card · base-model table· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 73.2% |
Data credits: Hugging Face official benchmark leaderboards; licence varies by benchmark · Data by LLM Stats · OpenEvals/leaderboard-data, MIT (licence) · 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.