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
51ChatGPT-4o Latest· Dubesor LLM Benchmark68%
52OpenAI o3· Dubesor LLM Benchmark68%
53GPT 4o· Dubesor LLM Benchmark67.9%
54Qwen 3 235B A22B· Dubesor LLM Benchmark67.6%
55Qwen3.5 397B A17B· Dubesor LLM Benchmark67.5%
56Grok 3 Minihigh· Dubesor LLM Benchmark67.3%
57Kimi K2.5· Dubesor LLM Benchmark67%
58GPT 5.4· Dubesor LLM Benchmark66.9%
59GPT-5.1 Codex· Dubesor LLM Benchmark66.8%
60Gemini 2.5 Flash Preview 05-20 (no think)thinking· Dubesor LLM Benchmark66.6%
61Kimi K2 Instruct· Dubesor LLM Benchmark66.4%
62DeepSeek V3.1· Dubesor LLM Benchmark66.3%
63Qwen3.5 Plus· Dubesor LLM Benchmark66.3%
64GLM 5· Dubesor LLM Benchmark66.1%
65GPT-5.1 Chat· Dubesor LLM Benchmark65.6%
66Gemma 4 26B A4B· Dubesor LLM Benchmark65.4%
67Llama 3.1 405B Instruct· Dubesor LLM Benchmark65.4%
68Qwen 3 235B A22B Thinking 2507· Dubesor LLM Benchmark65%
69GPT-5 mini· Dubesor LLM Benchmark64.7%
70o4 Mini· Dubesor LLM Benchmark64.7%
71Grok 3 Mini· Dubesor LLM Benchmark64.2%
72Qwen3.5 27Bthinking· Dubesor LLM Benchmark63.7%
73o3 Mini· Dubesor LLM Benchmark63.5%
74DeepSeek V3.1thinking· Dubesor LLM Benchmark63%
75Gemini 2.5 Flashthinking· Dubesor LLM Benchmark63%
76Qwen3.5 122B-A10B· Dubesor LLM Benchmark63%
77Claude 3.5 Sonnet· Dubesor LLM Benchmark62.4%
78DeepSeek V3· Dubesor LLM Benchmark62%
79GPT-5.2 Chat· Dubesor LLM Benchmark61.7%
80Grok 4 Fastreasoning· Dubesor LLM Benchmark61.5%
81Llama 3.3 70B Instruct· Dubesor LLM Benchmark61.5%
82GPT 4.1· Dubesor LLM Benchmark61.4%
83Claude Haiku 4.5thinking· Dubesor LLM Benchmark61.3%
84Grok 2· Dubesor LLM Benchmark61%
85Mistral Large 3· Dubesor LLM Benchmark61%
86GLM 4.5thinking· Dubesor LLM Benchmark60.8%
87GPT 4· Dubesor LLM Benchmark60.2%
88GLM 4.5· Dubesor LLM Benchmark60%
89gemini-2.5-flash-preview-04-17· Dubesor LLM Benchmark59.8%
90Step 3.5 Flash· Dubesor LLM Benchmark59.8%
91Llama 3.3 Nemotron Super 49B v1.5thinking· Dubesor LLM Benchmark59.7%
92Llama 3.3 Nemotron Super 49B v1thinking· Dubesor LLM Benchmark59.6%
93Qwen3 Next 80B A3Bthinking· Dubesor LLM Benchmark59.4%
94GLM 4.6· Dubesor LLM Benchmark59.2%
95Grok 4.20non-reasoning· Dubesor LLM Benchmark58.7%
96r1-1776· Dubesor LLM Benchmark58.6%
97Codex Mini· Dubesor LLM Benchmark58%
98Qwen3 Next 80B A3B Instruct· Dubesor LLM Benchmark57.8%
99MiMo V2 Omni· Dubesor LLM Benchmark57.4%
100GLM 4.7· Dubesor LLM Benchmark57.3%

Showing 51–100 of 270 results.