Skip to content

Benchmark

Dubesor Utility

Scores are percentages.

Models measured
224
Scores recorded
266
Sources
1
IQ weight
1.16

Score distribution

53.7%
Mean
55%
Median
17.9%
Std dev
28.7%
10th percentile
76.8%
90th percentile
4%
Min
4%87.4%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.16 for chat models, measured over 224 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
101Qwen 3 235B A22B· Dubesor LLM Benchmark61.7%
102Qwen3 30B A3B· Dubesor LLM Benchmark61.7%
103Claude Sonnet 4· Dubesor LLM Benchmark61.3%
104Llama 3.1 70B Instruct· Dubesor LLM Benchmark61.3%
105Llama 3.2 90B Vision Instruct· Dubesor LLM Benchmark61.3%
106MiMo V2 Omni· Dubesor LLM Benchmark61.2%
107GPT OSS 120B· Dubesor LLM Benchmark61%
108GPT-5.1 Chat· Dubesor LLM Benchmark60.1%
109Mixtral 8x7B Instruct v0.1· Dubesor LLM Benchmark60%
110Qwen3.5 27Bthinking· Dubesor LLM Benchmark60%
111GPT 5.4thinking· Dubesor LLM Benchmark59.5%
112OpenAI o3· Dubesor LLM Benchmark59.5%
113DeepSeek V2 Chat· Dubesor LLM Benchmark59%
114Olmo 3 32B Think· Dubesor LLM Benchmark59%
115Claude Haiku 3.5· Dubesor LLM Benchmark58.7%
116Devstral 2 123b Instruct 2512· Dubesor LLM Benchmark57.9%
117Qwen3 14Bthinking· Dubesor LLM Benchmark57.8%
118Gemini 2.5 Flash Preview 05-20 (no think)· Dubesor LLM Benchmark57.7%
119Grok 2· Dubesor LLM Benchmark57.7%
120GPT-4o mini· Dubesor LLM Benchmark57.4%
121Llama 3.3 Nemotron Super 49B v1.5thinking· Dubesor LLM Benchmark57.4%
122Nemotron 3 Super 120B A12B· Dubesor LLM Benchmark57.4%
123Grok 3· Dubesor LLM Benchmark57.2%
124Qwen3 Coder Next· Dubesor LLM Benchmark57.2%
125Gemini 2.0 Flash Lite· Dubesor LLM Benchmark56.8%
126Claude Sonnet 4.5· Dubesor LLM Benchmark56.6%
127Llama 3.2 11B Vision Instruct· Dubesor LLM Benchmark56.6%
128GPT 5.4· Dubesor LLM Benchmark56%
129GPT-5 mini· Dubesor LLM Benchmark56%
130Codex Mini· Dubesor LLM Benchmark55.3%
131Qwen2.5-Max· Dubesor LLM Benchmark55.1%
132GPT 5.4 Nano· Dubesor LLM Benchmark55%
133Mistral Large2402· Dubesor LLM Benchmark54.8%
134MiMo V2 Pro· Dubesor LLM Benchmark54.7%
135Gemini 1.5 Flash· Dubesor LLM Benchmark54.5%
136GPT 5.2· Dubesor LLM Benchmark54.3%
137Gemini 1.5 Flash-8B· Dubesor LLM Benchmark54.2%
138GLM 4.6v· Dubesor LLM Benchmark54.1%
139Qwen3.5 Plusthinking· Dubesor LLM Benchmark54%
140DeepSeek V2.5· Dubesor LLM Benchmark53.9%
141Mistral Medium· Dubesor LLM Benchmark53.8%
142DeepSeek R1 Zero· Dubesor LLM Benchmark53.6%
143Gemma 2 2B IT· Dubesor LLM Benchmark53.4%
144Qwen3 Max· Dubesor LLM Benchmark53.1%
145Olmo 2 32B Instruct· Dubesor LLM Benchmark53%
146Llama 3.1 Nemotron Ultra 253B v1thinking· Dubesor LLM Benchmark52.6%
147Llama 4 Scout· Dubesor LLM Benchmark52.5%
148Claude Sonnet 4thinking· Dubesor LLM Benchmark52.1%
149GLM 4· Dubesor LLM Benchmark52.1%
150Llama 3.1 Nemotron Ultra 253B v1· Dubesor LLM Benchmark52.1%

Showing 101–150 of 266 results.