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
51GPT-5 Codex· Dubesor LLM Benchmark70.7%
52Claude 3.5 Sonnet· Dubesor LLM Benchmark70.1%
53Claude Opus 4.6· Dubesor LLM Benchmark70%
54Claude 2.1· Dubesor LLM Benchmark68.8%
55Llama 3.1 8B Instruct· Dubesor LLM Benchmark68.8%
56Jamba 1.5 Large· Dubesor LLM Benchmark68.7%
57DeepSeek V3.1thinking· Dubesor LLM Benchmark68.3%
58Qwen3 235B A22B Instruct 2507· Dubesor LLM Benchmark68.2%
59Claude 3 Haiku· Dubesor LLM Benchmark68%
60Claude Opus 4· Dubesor LLM Benchmark67.8%
61Gemini 3 Pro Preview· Dubesor LLM Benchmark67.8%
62Gemini 3.1 Pro Preview· Dubesor LLM Benchmark67.8%
63Grok 3 Mini· Dubesor LLM Benchmark67.8%
64Qwen3 Next 80B A3Bthinking· Dubesor LLM Benchmark67.6%
65Llama 3 8B Instruct· Dubesor LLM Benchmark67.5%
66Llama 4 Maverick· Dubesor LLM Benchmark67.5%
67Step 3.5 Flash· Dubesor LLM Benchmark67.5%
68Gemini 2.5 Pro Preview 03-25· Dubesor LLM Benchmark67.4%
69Llama 3 70B Instruct· Dubesor LLM Benchmark67.4%
70Claude Sonnet 3.7thinking· Dubesor LLM Benchmark66.9%
71Gemini 2.5 Flash· Dubesor LLM Benchmark66.8%
72Gemini 2.5 Flashthinking· Dubesor LLM Benchmark66.8%
73Gemma 4 26B A4B· Dubesor LLM Benchmark66.8%
74GPT 4· Dubesor LLM Benchmark66.4%
75GLM 4.7thinking· Dubesor LLM Benchmark65.8%
76GLM 5thinking· Dubesor LLM Benchmark65.8%
77Qwen3.5 397B A17Bthinking· Dubesor LLM Benchmark65.8%
78o3 Mini· Dubesor LLM Benchmark65.4%
79GPT-3.5 Turbo· Dubesor LLM Benchmark64.8%
80Claude Opus 4thinking· Dubesor LLM Benchmark64.2%
81Claude Opus 4.1thinking· Dubesor LLM Benchmark64.2%
82GPT-5.1 Codex· Dubesor LLM Benchmark64.2%
83Qwen3.5 122B-A10B· Dubesor LLM Benchmark64.2%
84gemini-1.5-pro-002· Dubesor LLM Benchmark63.8%
85r1-1776· Dubesor LLM Benchmark63.5%
86Grok 4.20non-reasoning· Dubesor LLM Benchmark63.4%
87DeepSeek Coder V2 Instruct· Dubesor LLM Benchmark63.3%
88GLM 4.5 Airthinking· Dubesor LLM Benchmark63.1%
89Mistral Medium 3.1· Dubesor LLM Benchmark63.1%
90GLM 4.7· Dubesor LLM Benchmark63%
91Command A 03 2025· Dubesor LLM Benchmark62.8%
92Mistral Medium 3· Dubesor LLM Benchmark62.6%
93Claude Opus 4.1· Dubesor LLM Benchmark62.5%
94GLM 5· Dubesor LLM Benchmark62.4%
95Gemma 3 12B IT· Dubesor LLM Benchmark62.2%
96Gemma 4 26B A4Bthinking· Dubesor LLM Benchmark62%
97Qwen3-4B-Thinking-2507· Dubesor LLM Benchmark62%
98Claude Haiku 4.5· Dubesor LLM Benchmark61.8%
99Claude 3 Sonnet· Dubesor LLM Benchmark61.7%
100Llama 3.1 Nemotron 70B Instruct· Dubesor LLM Benchmark61.7%

Showing 51–100 of 266 results.