Skip to content

Benchmark

Dubesor Reason

Scores are percentages.

Models measured
218
Scores recorded
261
Sources
1
IQ weight
1.50

Score distribution

44.7%
Mean
42.8%
Median
24.3%
Std dev
11.2%
10th percentile
76.9%
90th percentile
0%
Min
0%93.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.50 for chat models, measured over 218 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
151MiniMax M2.1· Dubesor LLM Benchmark39.6%
152GPT-5.4 mini· Dubesor LLM Benchmark38.9%
153Qwen3 30B A3Bthinking· Dubesor LLM Benchmark38.6%
154Qwen2.5-Plus· Dubesor LLM Benchmark38.3%
155Qwen2 72B Instruct· Dubesor LLM Benchmark38.1%
156GLM Z1 32B 0414· Dubesor LLM Benchmark37.8%
157DeepSeek V2 Chat· Dubesor LLM Benchmark37.1%
158GPT OSS 120B· Dubesor LLM Benchmark37.1%
159Grok Code Fast 1· Dubesor LLM Benchmark37.1%
160GLM 4.7 Flashthinking· Dubesor LLM Benchmark37%
161Gemini 1.5 Flash· Dubesor LLM Benchmark36.4%
162Llama 3.1 Nemotron Ultra 253B v1· Dubesor LLM Benchmark36.4%
163Mistral Medium· Dubesor LLM Benchmark36.4%
164Qwen3.5 9B· Dubesor LLM Benchmark36.4%
165Grok 2 mini· Dubesor LLM Benchmark35.3%
166Qwen3 Coder Plus· Dubesor LLM Benchmark35.1%
167Gemini 2.5 Flash-Lite· Dubesor LLM Benchmark34.9%
168Qwen2.5 32B Instruct· Dubesor LLM Benchmark34.9%
169Qwen3-4B-Thinking-2507· Dubesor LLM Benchmark34.9%
170Claude 3 Opus· Dubesor LLM Benchmark34%
171GPT-5 nano· Dubesor LLM Benchmark33.6%
172Qwen3.5 4Bthinking· Dubesor LLM Benchmark33.2%
173Llama 3.1 70B Instruct· Dubesor LLM Benchmark33.1%
174Grok 4 Fastnon-reasoning· Dubesor LLM Benchmark32.8%
175MiMo V2 Flash· Dubesor LLM Benchmark32.7%
176Magistral Small 2509· Dubesor LLM Benchmark31.7%
177ERNIE 4.5 300B A47B· Dubesor LLM Benchmark31.4%
178GPT OSS 20b· Dubesor LLM Benchmark29.7%
179Llama 3 70B Instruct· Dubesor LLM Benchmark29.4%
180QVQ 72B Preview· Dubesor LLM Benchmark29.3%
181Qwen3 4Bthinking· Dubesor LLM Benchmark29.1%
182Qwen3 VL 8B Instruct· Dubesor LLM Benchmark28.8%
183GLM 4.5 Air· Dubesor LLM Benchmark27.9%
184GPT-4o mini· Dubesor LLM Benchmark27.9%
185Llama 4 Scout· Dubesor LLM Benchmark27.8%
186Hunyuan A13B Instructthinking· Dubesor LLM Benchmark27.2%
187DeepSeek V2.5· Dubesor LLM Benchmark26.4%
188Gemini 2.0 Flash Lite· Dubesor LLM Benchmark26.3%
189MiniMax 01· Dubesor LLM Benchmark26.3%
190WizardLM 2 8x22B· Dubesor LLM Benchmark26.2%
191Qwen 2.5 14B Instruct· Dubesor LLM Benchmark25.9%
192Nemotron 3 Nano 30B A3Bthinking· Dubesor LLM Benchmark25.1%
193Qwen3 8B· Dubesor LLM Benchmark24.5%
194Inflection 3 Productivity· Dubesor LLM Benchmark24.3%
195Gemma 3 12B IT· Dubesor LLM Benchmark24.2%
196Qwen3 Coder 30B A3B Instruct· Dubesor LLM Benchmark24.1%
197GLM 4.6v· Dubesor LLM Benchmark23.7%
198Qwen3 4B· Dubesor LLM Benchmark23.3%
199Olmo 3 7B Think· Dubesor LLM Benchmark23%
200GLM 4 32B· Dubesor LLM Benchmark22.7%

Showing 151–200 of 261 results.