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
1Claude Sonnet 4.6· Dubesor LLM Benchmark86.1%
2Gemini 3 Pro Preview· Dubesor LLM Benchmark85.3%
3Claude Opus 4.7· Dubesor LLM Benchmark83.3%
4Claude Opus 4thinking· Dubesor LLM Benchmark82.8%
5Claude Opus 4.1thinking· Dubesor LLM Benchmark82.7%
6Gemini 3.1 Pro Preview· Dubesor LLM Benchmark82.6%
7Claude Opus 4.1· Dubesor LLM Benchmark81.9%
8Claude Opus 4· Dubesor LLM Benchmark81.5%
9Claude Opus 4.5· Dubesor LLM Benchmark81.2%
10Claude Opus 4.6· Dubesor LLM Benchmark81.2%
11Claude Sonnet 4· Dubesor LLM Benchmark79.9%
12GPT-4 Turbo· Dubesor LLM Benchmark79.5%
13Grok 4· Dubesor LLM Benchmark79.3%
14Gemma 4 31B IT· Dubesor LLM Benchmark78.7%
15Gemini 2.5 Pro· Dubesor LLM Benchmark78.5%
16GPT-4.5 Preview· Dubesor LLM Benchmark78.5%
17Gemini 2.5 Pro Preview 05-06· Dubesor LLM Benchmark78.4%
18Gemini 2.5 Pro Preview 03-25· Dubesor LLM Benchmark78.3%
19DeepSeek V3.2 Speciale· Dubesor LLM Benchmark76.9%
20Grok 4.20reasoning· Dubesor LLM Benchmark76.8%
21Gemini 3 Flashthinking· Dubesor LLM Benchmark76.5%
22Gemini 3 Flash· Dubesor LLM Benchmark75.8%
23GPT 5· Dubesor LLM Benchmark75.8%
24Claude Sonnet 4thinking· Dubesor LLM Benchmark74.7%
25GLM 5thinking· Dubesor LLM Benchmark74.6%
26Kimi K2.5thinking· Dubesor LLM Benchmark74.3%
27Claude Sonnet 4.5· Dubesor LLM Benchmark73.8%
28DeepSeek R1· Dubesor LLM Benchmark73.4%
29GPT 5.2· Dubesor LLM Benchmark73.2%
30Claude Sonnet 3.7· Dubesor LLM Benchmark73%
31Gemini 3.1 Flash Lite· Dubesor LLM Benchmark73%
32GLM 4.6thinking· Dubesor LLM Benchmark72.9%
33GPT 5.4thinking· Dubesor LLM Benchmark72.8%
34Kimi K2 Thinking· Dubesor LLM Benchmark72.7%
35Qwen3.5 397B A17Bthinking· Dubesor LLM Benchmark72.7%
36Qwen3.5 Plusthinking· Dubesor LLM Benchmark72.7%
37Qwen3 Max· Dubesor LLM Benchmark72.3%
38Gemma 4 26B A4Bthinking· Dubesor LLM Benchmark71.9%
39GPT-5 Chat· Dubesor LLM Benchmark71.4%
40Claude Sonnet 3.7thinking· Dubesor LLM Benchmark71%
41DeepSeek V3.2· Dubesor LLM Benchmark70.7%
42DeepSeek R1 Zero· Dubesor LLM Benchmark70.5%
43Qwen3 235B A22B Instruct 2507· Dubesor LLM Benchmark70.5%
44Grok 3· Dubesor LLM Benchmark70.4%
45gemini-2.5-flash-preview-04-17thinking· Dubesor LLM Benchmark69.9%
46MiMo V2 Pro· Dubesor LLM Benchmark69.7%
47GLM 4.7thinking· Dubesor LLM Benchmark69.6%
48GPT 5.1· Dubesor LLM Benchmark69.3%
49GPT-5 Codex· Dubesor LLM Benchmark69.3%
50o1· Dubesor LLM Benchmark68.8%

Showing 1–50 of 270 results.