Skip to content

Benchmark

DROP

Scores are percentages. Higher is better.

Models and systems measured
24
Scores recorded
24
Sources
2
IQ weight
2.04

Score distribution

78.7%
Mean
80.9%
Median
12.2%
Std dev
70.2%
10th percentile
87.1%
90th percentile
28.6%
Min
28.6%91.6%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.04 for chat models, measured over 22 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#Model or systemScore
1DeepSeek V3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim91.6%
2Claude 3.5 Sonnet· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim87.1%
3MiMo V2.5 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim86.3%
4GPT-4 Turbo· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim86%
5Nova Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim85.4%
6Llama 3.1 405B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim84.8%
7GPT 4o· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim83.4%
8Claude 3 Opus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim83.1%
9Claude Haiku 3.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim83.1%
10GPT 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim80.9%
11Nova Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim80.2%
12GPT-4o mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim79.7%
13Llama 3.1 70B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim79.6%
14Nova Micro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim79.3%
15LongCat Flash Chat· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim79.1%
16Claude 3 Sonnet· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78.9%
17Claude 3 Haiku· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78.4%
18Phi 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim75.5%
19Gemini 1.5 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim74.9%
20GPT-3.5 Turbo· LLM Stats data70.2%
21Llama 3.1 8B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim59.5%
22ERNIE 4.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim28.6%

Not ranked

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

Model or systemScore
DeepSeek V4.1 Flash BaseF1 · 1-shot· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.87.9%
MiMo V2 Flash Baseofficial Base table · 3-shot· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.84.7%

Data credits: Data by LLM Stats · BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.