Skip to content

Benchmark

Creative Writing v3

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
0.8032,176.9
The band covers the middle 80% of scores. The line marks the median.

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

#ModelScore
101Gemini 2.0 Flash· EQ-Bench boards1,131.1
102Gemma 4 E4B-it· EQ-Bench boards1,092.8
103GLM 4 32B· EQ-Bench boards1,066.7
104Gemma 3 4B IT· EQ-Bench boards1,065.7
105Mistral Large· EQ-Bench boards982.1
106GPT OSS 120B· EQ-Bench boards956
107GPT-4.1 nano· EQ-Bench boards938.7
108Mistral Nemo· EQ-Bench boards877.5
109GPT-4o mini· EQ-Bench boards870.8
110Llama 3.1 405B Instruct· EQ-Bench boards868.1
111Llama 4 Maverick· EQ-Bench boards858.1
112Gemma 2 9B IT· EQ-Bench boards839.8
113Llama 3.1 70B Instruct· EQ-Bench boards781.7
114Llama 4 Scout· EQ-Bench boards781.1
115Mistral Small 3.1 24b Instruct 2503· EQ-Bench boards759
116GPT 4· EQ-Bench boards750.4
117LFM-7b· EQ-Bench boards750
118Claude 3 Haiku· EQ-Bench boards715.7
119Llama 3.1 8B Instruct· EQ-Bench boards711.3
120Mistral Small 24B Instruct· EQ-Bench boards704.9
121GPT-5 nano· EQ-Bench boards703.3
122GPT OSS 20b· EQ-Bench boards664.5
123Llama 3.2 3B· EQ-Bench boards594.1
124GPT-3.5 Turbo· EQ-Bench boards450.3
125Llama 3.2 1B Instruct· EQ-Bench boards200
126Qwen3 235B A22B Instruct 2507· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim0.875
127Qwen3 VL 235B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.0.865
128Qwen 3 235B A22B Thinking 2507· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim0.861
129Grok 4.1thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim0.861
130Qwen3 VL 235Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.0.857
131Qwen3 VL 32B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.0.856
132Grok 4.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim0.854
133Qwen3 Next 80B A3B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim0.853
134qwen3-vl-30b· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.0.846
135Qwen3 VL 32B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.0.833
136qwen3-vl-30bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.0.825
137Qwen: Qwen3 VL 8B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.0.824
138Qwen3 14B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim0.803

Showing 101–138 of 138 results.

Data credits: EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · Data by LLM Stats