Benchmark
Creative Writing v3
Scores from EQ-Bench boards, LLM Stats data.
- Models measured
- 135
- Scores recorded
- 138
- Sources
- 2
- IQ weight
- 1.57
Score distribution
- 1,302.9
- Mean
- 1,436.1
- Median
- 572.4
- Std dev
- 450.3
- 10th percentile
- 1,914.9
- 90th percentile
- 0.803
- Min
This benchmark has a weight of 1.57 for chat models, measured over 135 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 |
|---|---|---|
| 101 | Gemini 2.0 Flash· EQ-Bench boards | 1,131.1 |
| 102 | Gemma 4 E4B-it· EQ-Bench boards | 1,092.8 |
| 103 | GLM 4 32B· EQ-Bench boards | 1,066.7 |
| 104 | Gemma 3 4B IT· EQ-Bench boards | 1,065.7 |
| 105 | Mistral Large· EQ-Bench boards | 982.1 |
| 106 | GPT OSS 120B· EQ-Bench boards | 956 |
| 107 | GPT-4.1 nano· EQ-Bench boards | 938.7 |
| 108 | Mistral Nemo· EQ-Bench boards | 877.5 |
| 109 | GPT-4o mini· EQ-Bench boards | 870.8 |
| 110 | Llama 3.1 405B Instruct· EQ-Bench boards | 868.1 |
| 111 | Llama 4 Maverick· EQ-Bench boards | 858.1 |
| 112 | Gemma 2 9B IT· EQ-Bench boards | 839.8 |
| 113 | Llama 3.1 70B Instruct· EQ-Bench boards | 781.7 |
| 114 | Llama 4 Scout· EQ-Bench boards | 781.1 |
| 115 | Mistral Small 3.1 24b Instruct 2503· EQ-Bench boards | 759 |
| 116 | GPT 4· EQ-Bench boards | 750.4 |
| 117 | LFM-7b· EQ-Bench boards | 750 |
| 118 | Claude 3 Haiku· EQ-Bench boards | 715.7 |
| 119 | Llama 3.1 8B Instruct· EQ-Bench boards | 711.3 |
| 120 | Mistral Small 24B Instruct· EQ-Bench boards | 704.9 |
| 121 | GPT-5 nano· EQ-Bench boards | 703.3 |
| 122 | GPT OSS 20b· EQ-Bench boards | 664.5 |
| 123 | Llama 3.2 3B· EQ-Bench boards | 594.1 |
| 124 | GPT-3.5 Turbo· EQ-Bench boards | 450.3 |
| 125 | Llama 3.2 1B Instruct· EQ-Bench boards | 200 |
| 126 | Qwen3 235B A22B Instruct 2507· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 0.875 |
| 127 | Qwen3 VL 235B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 0.865 |
| 128 | Qwen 3 235B A22B Thinking 2507· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 0.861 |
| 129 | Grok 4.1thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 0.861 |
| 130 | Qwen3 VL 235Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 0.857 |
| 131 | Qwen3 VL 32B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 0.856 |
| 132 | Grok 4.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 0.854 |
| 133 | Qwen3 Next 80B A3B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 0.853 |
| 134 | qwen3-vl-30b· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 0.846 |
| 135 | Qwen3 VL 32B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 0.833 |
| 136 | qwen3-vl-30bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 0.825 |
| 137 | Qwen: Qwen3 VL 8B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 0.824 |
| 138 | Qwen3 14B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 0.803 |
Showing 101–138 of 138 results.
Data credits: EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · Data by LLM Stats