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
1Gemini 3 Pro Preview· Dubesor LLM Benchmark93.3%
2Gemini 3.1 Pro Preview· Dubesor LLM Benchmark91.7%
3Claude Opus 4· Dubesor LLM Benchmark91.5%
4Claude Opus 4thinking· Dubesor LLM Benchmark91.4%
5Claude Opus 4.1thinking· Dubesor LLM Benchmark90.4%
6Claude Sonnet 4.6· Dubesor LLM Benchmark89.7%
7Claude Opus 4.6· Dubesor LLM Benchmark88.4%
8Gemini 2.5 Pro· Dubesor LLM Benchmark87.8%
9GLM 5thinking· Dubesor LLM Benchmark87.6%
10Claude Sonnet 4· Dubesor LLM Benchmark87.5%
11Claude Opus 4.1· Dubesor LLM Benchmark86.2%
12Gemma 4 31B IT· Dubesor LLM Benchmark85.8%
13Claude Sonnet 4.5· Dubesor LLM Benchmark85.7%
14Gemini 2.5 Pro Preview 03-25· Dubesor LLM Benchmark85.7%
15Claude Sonnet 4thinking· Dubesor LLM Benchmark85.6%
16Qwen3 Max· Dubesor LLM Benchmark85.5%
17Qwen3.5 Plusthinking· Dubesor LLM Benchmark84.2%
18Claude Opus 4.7· Dubesor LLM Benchmark83.7%
19Grok 4· Dubesor LLM Benchmark83.5%
20Claude Opus 4.5· Dubesor LLM Benchmark82.1%
21Qwen3.5 397B A17Bthinking· Dubesor LLM Benchmark81.7%
22GPT-4.5 Preview· Dubesor LLM Benchmark81.5%
23Gemini 2.5 Pro Preview 05-06· Dubesor LLM Benchmark80.5%
24Qwen3.5 397B A17B· Dubesor LLM Benchmark78.3%
25Gemini 3 Flashthinking· Dubesor LLM Benchmark77.3%
26MiMo V2 Pro· Dubesor LLM Benchmark77.3%
27Qwen3.5 27Bthinking· Dubesor LLM Benchmark76.9%
28GPT 5.2· Dubesor LLM Benchmark76.8%
29GPT-5 Codex· Dubesor LLM Benchmark76.5%
30GPT-5 Chat· Dubesor LLM Benchmark76.4%
31Qwen3.5 Plus· Dubesor LLM Benchmark76.3%
32Kimi K2.5thinking· Dubesor LLM Benchmark75.6%
33Claude Sonnet 3.7· Dubesor LLM Benchmark75.5%
34Gemma 4 26B A4Bthinking· Dubesor LLM Benchmark75.5%
35GPT 5.4thinking· Dubesor LLM Benchmark75.5%
36GLM 4.6thinking· Dubesor LLM Benchmark75.3%
37Gemini 3 Flash· Dubesor LLM Benchmark73.9%
38GPT 5· Dubesor LLM Benchmark73.7%
39Kimi K2 Thinking· Dubesor LLM Benchmark73.6%
40gemini-2.5-flash-preview-04-17thinking· Dubesor LLM Benchmark73.4%
41GPT-5.1 Codex· Dubesor LLM Benchmark72.7%
42Gemini 3.1 Flash Lite· Dubesor LLM Benchmark72.3%
43GLM 5· Dubesor LLM Benchmark72.2%
44GPT 5.1· Dubesor LLM Benchmark72.1%
45DeepSeek V3.2 Speciale· Dubesor LLM Benchmark71.9%
46GLM 4.7thinking· Dubesor LLM Benchmark71.6%
47Qwen3 235B A22B Instruct 2507· Dubesor LLM Benchmark71.5%
48GPT-5.2 Chat· Dubesor LLM Benchmark71.2%
49GPT-4 Turbo· Dubesor LLM Benchmark70.7%
50Claude Sonnet 3.7thinking· Dubesor LLM Benchmark68.7%

Showing 1–50 of 261 results.