Benchmark
MMLU
Scores are percentages. Higher is better.
- Models and systems measured
- 138
- Scores recorded
- 153
- Sources
- 3
- IQ weight
- 0.00
Score distribution
- 76.9%
- Mean
- 80.1%
- Median
- 12.2%
- Std dev
- 60.1%
- 10th percentile
- 88.8%
- 90th percentile
- 36.6%
- Min
This benchmark has a weight of 0.00 for chat models, measured over 133 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 |
|---|---|---|
| 51 | qwen3-vl-30b· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 85% |
| 52 | Phi 4· Epoch AI Benchmarking Hub dataValues from 2 sources
| 84.8% |
| 53 | Llama 3.1 405B· Epoch AI Benchmarking Hub data | 84.4% |
| 54 | GPT OSS 20bofficial model card Table 3 · reasoning medium · published setting; Table 3 does not further specify tool access · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 84% |
| 55 | Mistral Large 2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 84% |
| 56 | 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
| 83.6% |
| 57 | Llama 3.1 70B Instruct5-shot · macro_avg/acc· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 83.6% |
| 58 | Qwen2.5 32B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 83.3% |
| 59 | Qwen2 72B Instruct· Epoch AI Benchmarking Hub dataValues from 2 sources
| 82.4% |
| 60 | GPT-4o mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 82% |
| 61 | Nova Prov1· Epoch AI Benchmarking Hub data | 82% |
| 62 | Jamba 1.5 Large· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 81.2% |
| 63 | Qwen3 VL 8B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 80.7% |
| 64 | 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 | 80.6% |
| 65 | Mistral Small 3.2 24B Instruct2506· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 80.5% |
| 66 | Nova Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 80.5% |
| 67 | DeepSeek V2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 80.4% |
| 68 | GPT OSS 20bofficial model card Table 3 · reasoning low · published setting; Table 3 does not further specify tool access · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 80.4% |
| 69 | Llama 3.2 90B Vision Instruct· Epoch AI Benchmarking Hub data | 80.3% |
| 70 | Llama 3.1 Nemotron 70B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 80.2% |
| 71 | GPT-4.1 nano· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 80.1% |
| 72 | Mistral Large2407· Epoch AI Benchmarking Hub data | 80% |
| 73 | Qwen 2.5 14B Instruct· Epoch AI Benchmarking Hub dataValues from 2 sources
| 79.9% |
| 74 | Gemini 2.0 Flash Experimental· Epoch AI Benchmarking Hub data | 79.7% |
| 75 | Llama 4 Scout· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 79.6% |
| 76 | Llama 3 70B Instruct· Epoch AI Benchmarking Hub data | 79.3% |
| 77 | yi-large· Epoch AI Benchmarking Hub data | 79.3% |
| 78 | Qwen 2.5 Coder 32B· Epoch AI Benchmarking Hub data | 79.1% |
| 79 | Claude 3 Sonnet· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 79% |
| 80 | Gemini 1.5 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 78.9% |
| 81 | phi-3.5-moe-instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 78.9% |
| 82 | Claude 2· Epoch AI Benchmarking Hub data | 78.5% |
| 83 | Phi-3 Medium 128K Instruct· Epoch AI Benchmarking Hub data | 78% |
| 84 | gemini-1.5-flash-001· Epoch AI Benchmarking Hub data | 77.9% |
| 85 | mixtral-8x22b-v0.1· Epoch AI Benchmarking Hub data | 77.8% |
| 86 | Nova Micro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 77.6% |
| 87 | Nova Litev1· Epoch AI Benchmarking Hub data | 77% |
| 88 | Yi-34B· Epoch AI Benchmarking Hub data | 76.3% |
| 89 | Command R Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 75.7% |
| 90 | Gemma 2 27B IT· Epoch AI Benchmarking Hub dataValues from 2 sources
| 75.7% |
| 91 | Phi-3 Small 8K Instruct· Epoch AI Benchmarking Hub data | 75.7% |
| 92 | Claude 3 Haiku· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 75.2% |
| 93 | qwen2p5-coder-14b· Epoch AI Benchmarking Hub data | 75.2% |
| 94 | Qwen 2.5 Coder 32B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 75.1% |
| 95 | Claude Haiku 3.5· Epoch AI Benchmarking Hub data | 74.3% |
| 96 | gemini-1.5-flash-002· Epoch AI Benchmarking Hub data | 73.9% |
| 97 | Claude 2.1· Epoch AI Benchmarking Hub data | 73.5% |
| 98 | Yi 34B Chat· Epoch AI Benchmarking Hub data | 73.5% |
| 99 | Claude Instant 1.2· Epoch AI Benchmarking Hub data | 73.2% |
| 100 | Llama 3.2 11B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 73% |
Showing 51–100 of 148 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 |
|---|---|
| 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. | 86.7% |
| 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. | 88.6% |
| 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. | 90.4% |
| 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. | 87.5% |
| 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. | 90.4% |
Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · 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.