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
151Qwen3 VL 8B Instruct· Dubesor LLM Benchmark52.1%
152o1· Dubesor LLM Benchmark52%
153Qwen3 VL 32B Instruct· Dubesor LLM Benchmark52%
154LongCat Flash Chat· Dubesor LLM Benchmark51.8%
155qwen3-vl-30b· Dubesor LLM Benchmark51.8%
156Qwen3 8Bthinking· Dubesor LLM Benchmark51.4%
157GPT OSS 20b· Dubesor LLM Benchmark50.4%
158Qwen3.5 35B A3Bthinking· Dubesor LLM Benchmark50.4%
159Qwen3.5 9Bthinking· Dubesor LLM Benchmark50.4%
160MiniMax M2· Dubesor LLM Benchmark49.9%
161Grok 4 Fastnon-reasoning· Dubesor LLM Benchmark49.3%
162o4 Mini· Dubesor LLM Benchmark49.2%
163Qwen3.5 Plus· Dubesor LLM Benchmark49.2%
164Qwen3.5 397B A17B· Dubesor LLM Benchmark48.9%
165Jamba 1.5 Mini· Dubesor LLM Benchmark48.8%
166Qwen3 Next 80B A3B Instruct· Dubesor LLM Benchmark48.7%
167Gemma 3n E4B IT· Dubesor LLM Benchmark48.5%
168Qwen3 14B· Dubesor LLM Benchmark48.3%
169GPT-5.1 Codex Mini· Dubesor LLM Benchmark48.2%
170Inflection 3 Productivity· Dubesor LLM Benchmark48.2%
171Ministral 3B· Dubesor LLM Benchmark48%
172Nemotron 3 Nano 30B A3B· Dubesor LLM Benchmark47.5%
173GLM 4.6vthinking· Dubesor LLM Benchmark47.4%
174Ling 1t· Dubesor LLM Benchmark47.3%
175Nemotron 3 Nano 30B A3Bthinking· Dubesor LLM Benchmark47.3%
176Yi Lightning· Dubesor LLM Benchmark47.3%
177MiniMax M1· Dubesor LLM Benchmark47.1%
178Mistral Small 3.2 24B Instruct· Dubesor LLM Benchmark47%
179Phi 4 Reasoning Plus· Dubesor LLM Benchmark47%
180Olmo 3 7B Instruct· Dubesor LLM Benchmark46.8%
181Nemotron 3 Super 120B A12Bthinking· Dubesor LLM Benchmark46.7%
182Command R+· Dubesor LLM Benchmark46.6%
183Llama 3.3 Nemotron Super 49B v1· Dubesor LLM Benchmark46.6%
184Mistral Small 3.1 24b Instruct 2503· Dubesor LLM Benchmark46.6%
185Qwen3 30B A3Bthinking· Dubesor LLM Benchmark46.6%
186Llama 2 70B Chat· Dubesor LLM Benchmark46.3%
187Claude 3 Opus· Dubesor LLM Benchmark45.8%
188Grok Code Fast 1· Dubesor LLM Benchmark45.8%
189Qwen3.5 35B A3B· Dubesor LLM Benchmark45.3%
190Qwen3 Coder Plus· Dubesor LLM Benchmark45.1%
191MiMo V2 Flash· Dubesor LLM Benchmark45%
192GPT 5.1· Dubesor LLM Benchmark44.4%
193Claude Haiku 4.5thinking· Dubesor LLM Benchmark44%
194GLM 4 32B· Dubesor LLM Benchmark42.8%
195Magistral Medium2506· Dubesor LLM Benchmark42.8%
196Qwen2.5-Plus· Dubesor LLM Benchmark42.8%
197Reka Core· Dubesor LLM Benchmark42.6%
198GPT-4.1 nano· Dubesor LLM Benchmark42.4%
199Llama 3.3 Nemotron Super 49B v1.5· Dubesor LLM Benchmark41.9%
200Ministral 8B· Dubesor LLM Benchmark41.8%

Showing 151–200 of 266 results.