Skip to content

Benchmark

Dubesor Total

Scores are percentages.

Models measured
227
Scores recorded
270
Sources
1
IQ weight
1.57

Score distribution

48.3%
Mean
50.7%
Median
20.5%
Std dev
18.3%
10th percentile
73.4%
90th percentile
0.2%
Min
0.2%86.1%
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 227 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
151GPT-5 nano· Dubesor LLM Benchmark47.2%
152Qwen3 VL 32B Instruct· Dubesor LLM Benchmark47%
153Qwen2.5 72B Instruct· Dubesor LLM Benchmark46.9%
154Claude 3 Opus· Dubesor LLM Benchmark46.7%
155Mistral Large2402· Dubesor LLM Benchmark46.6%
156Command A 03 2025· Dubesor LLM Benchmark46.5%
157MiniMax M2.1· Dubesor LLM Benchmark46.5%
158Grok 4 Fastnon-reasoning· Dubesor LLM Benchmark46.4%
159Olmo 3 32B Think· Dubesor LLM Benchmark46.3%
160QwQ 32B· Dubesor LLM Benchmark46.3%
161Llama 3.1 70B Instruct· Dubesor LLM Benchmark46.2%
162GLM 4.7 Flashthinking· Dubesor LLM Benchmark45.7%
163qwen3-vl-30b· Dubesor LLM Benchmark45.6%
164Yi Lightning· Dubesor LLM Benchmark45.6%
165DeepSeek R1 0528 Qwen3 8B· Dubesor LLM Benchmark44.7%
166GPT OSS 20b· Dubesor LLM Benchmark44.5%
167Qwen3-4B-Thinking-2507· Dubesor LLM Benchmark43.9%
168Magistral Small 2509· Dubesor LLM Benchmark43.8%
169Mistral Medium· Dubesor LLM Benchmark43.6%
170GLM 4.5 Air· Dubesor LLM Benchmark43.4%
171GLM 4.6v· Dubesor LLM Benchmark43.1%
172yi-large· Dubesor LLM Benchmark42.8%
173Grok 2 mini· Dubesor LLM Benchmark42.6%
174Claude Haiku 3.5· Dubesor LLM Benchmark41.2%
175Qwen3 32B· Dubesor LLM Benchmark40.8%
176gemini-1.5-flash-002· Dubesor LLM Benchmark40.6%
177ERNIE 4.5 300B A47B· Dubesor LLM Benchmark40.4%
178GLM Z1 32B 0414· Dubesor LLM Benchmark40.3%
179Gemini 2.0 Flash Lite· Dubesor LLM Benchmark40.1%
180Gemini 1.5 Pro· Dubesor LLM Benchmark40%
181Llama 3 70B Instruct· Dubesor LLM Benchmark40%
182Jamba 1.5 Large· Dubesor LLM Benchmark39.8%
183Nemotron-4 340B Instruct· Dubesor LLM Benchmark39.5%
184Mistral Small 3.1 24b Instruct 2503· Dubesor LLM Benchmark39.3%
185Mistral Small 3.2 24B Instruct· Dubesor LLM Benchmark38.7%
186WizardLM 2 8x22B· Dubesor LLM Benchmark37.7%
187Nemotron 3 Nano 30B A3Bthinking· Dubesor LLM Benchmark37.5%
188Llama 4 Scout· Dubesor LLM Benchmark36.7%
189DeepSeek Coder V2 Instruct· Dubesor LLM Benchmark36%
190MiniMax 01· Dubesor LLM Benchmark35.9%
191Qwen3.5 9B· Dubesor LLM Benchmark35.8%
192Qwen2 72B Instruct· Dubesor LLM Benchmark35.2%
193GLM 4· Dubesor LLM Benchmark35%
194Qwen3 4Bthinking· Dubesor LLM Benchmark34.3%
195Qwen2.5 32B Instruct· Dubesor LLM Benchmark34.2%
196Qwen3 VL 8B Instruct· Dubesor LLM Benchmark34%
197Gemma 3 27B IT· Dubesor LLM Benchmark33.6%
198Qwen3 Coder 30B A3B Instruct· Dubesor LLM Benchmark33.6%
199Qwen3.5 4Bthinking· Dubesor LLM Benchmark33.5%
200Qwen3 14B· Dubesor LLM Benchmark33.2%

Showing 151–200 of 270 results.