Skip to content

Benchmark

Dubesor Tech

Scores are percentages.

Models measured
214
Scores recorded
255
Sources
1
IQ weight
1.67

Score distribution

55.2%
Mean
61.2%
Median
24.4%
Std dev
16.5%
10th percentile
81.1%
90th percentile
2.3%
Min
2.3%95.8%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.67 for chat models, measured over 214 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 Opus 4.1· Dubesor LLM Benchmark95.8%
2Claude Opus 4.5· Dubesor LLM Benchmark95.8%
3Claude Opus 4.6· Dubesor LLM Benchmark95.8%
4Claude Opus 4.7· Dubesor LLM Benchmark95.8%
5Claude Opus 4.1thinking· Dubesor LLM Benchmark93.9%
6GPT-4 Turbo· Dubesor LLM Benchmark91%
7MiMo V2 Pro· Dubesor LLM Benchmark89.9%
8Claude Opus 4thinking· Dubesor LLM Benchmark89.7%
9Gemini 3 Pro Preview· Dubesor LLM Benchmark89.7%
10Claude Sonnet 4.6· Dubesor LLM Benchmark86.2%
11Claude Sonnet 4.5· Dubesor LLM Benchmark85.8%
12Claude Haiku 4.5thinking· Dubesor LLM Benchmark85.7%
13o4 Mini· Dubesor LLM Benchmark85.6%
14Claude Opus 4· Dubesor LLM Benchmark85.5%
15DeepSeek V3· Dubesor LLM Benchmark85.5%
16Gemini 2.5 Pro Preview 05-06· Dubesor LLM Benchmark85.5%
17Gemini 3 Flash· Dubesor LLM Benchmark85.5%
18Qwen3.5 397B A17Bthinking· Dubesor LLM Benchmark85.5%
19Qwen3.5 Plusthinking· Dubesor LLM Benchmark85.5%
20Claude Haiku 4.5· Dubesor LLM Benchmark84.6%
21GPT 4o· Dubesor LLM Benchmark84.6%
22Gemini 3.1 Pro Preview· Dubesor LLM Benchmark84.3%
23Claude Sonnet 4· Dubesor LLM Benchmark83.8%
24GPT 5.4thinking· Dubesor LLM Benchmark83.8%
25Grok 3· Dubesor LLM Benchmark81.8%
26GPT 5.2· Dubesor LLM Benchmark81.4%
27GPT 5· Dubesor LLM Benchmark81.1%
28GPT-4.5 Preview· Dubesor LLM Benchmark81.1%
29Claude Sonnet 3.7thinking· Dubesor LLM Benchmark81%
30Qwen3 Max· Dubesor LLM Benchmark80.4%
31Claude Sonnet 4thinking· Dubesor LLM Benchmark80.1%
32DeepSeek Coder V2 Instruct· Dubesor LLM Benchmark80.1%
33DeepSeek R1· Dubesor LLM Benchmark80.1%
34Gemini 2.5 Pro· Dubesor LLM Benchmark80.1%
35Gemini 2.5 Pro Preview 03-25· Dubesor LLM Benchmark80.1%
36Gemini 3 Flashthinking· Dubesor LLM Benchmark80.1%
37GPT-5 Codex· Dubesor LLM Benchmark80.1%
38Kimi K2.5thinking· Dubesor LLM Benchmark80.1%
39MiniMax M1· Dubesor LLM Benchmark80.1%
40ChatGPT-4o Latest· Dubesor LLM Benchmark79.9%
41Command A 03 2025· Dubesor LLM Benchmark79.7%
42Codex Mini· Dubesor LLM Benchmark79.6%
43DeepSeek V3.2 Speciale· Dubesor LLM Benchmark79.6%
44Gemini 2.5 Flash Preview 05-20 (no think)thinking· Dubesor LLM Benchmark79.6%
45Gemma 4 26B A4Bthinking· Dubesor LLM Benchmark79.6%
46Gemma 4 31B IT· Dubesor LLM Benchmark79.6%
47GPT 5.4· Dubesor LLM Benchmark79.6%
48GPT-4o mini· Dubesor LLM Benchmark79.6%
49GPT-5.4 mini· Dubesor LLM Benchmark79.6%
50Grok 4.20non-reasoning· Dubesor LLM Benchmark79.6%

Showing 1–50 of 255 results.