Categorization Bench

This benchmark measures the model's ability to suggest relevant category names for a given set of related concepts or items.

May 16, 2026

10 tasks

110 models

$2.1665

karllorey

Public

ResultsPreliminary

Vote in the arena

54 of 110 models on the leaderboard so far. More join with each arena vote.

GPT-5.5

by OpenAI

5.6s

$0.0525

100%

score

Gemini 2.5 Pro

by Google

15.3s

$0.1209

90%

score

Claude Opus 4.6

by Anthropic

3.6s

$0.0220

79%

score

Claude Sonnet 4.6

by Anthropic

2.8s

$0.0109

77%

score

Llama 4 Scout

by Meta

1.1s

$0.0003

76%

score

Prompt Details

Expand each prompt to see per-model responses and reasoning.

Model Comparison

Compare performance across models and prompts.

GPT-5.5

by OpenAI on OpenRouter

5.6s

$0.0525

100%

Gemini 2.5 Pro

by Google on OpenRouter

15.3s

$0.1209

90%

Claude Opus 4.6

by Anthropic on OpenRouter

3.6s

$0.0220

79%

Claude Sonnet 4.6

by Anthropic on OpenRouter

2.8s

$0.0109

77%

Llama 4 Scout

by Meta on OpenRouter

1.1s

$0.0003

76%

Llama 3.3 70B Instruct

by Meta on OpenRouter

3.1s

$0.0003

74%

gpt-oss-20b

by OpenAI on OpenRouter

4.2s

$0.0005

73%

Claude Opus 4.7

by Anthropic on OpenRouter

3.3s

$0.0285

70%

GLM 5.1

by Z.ai on OpenRouter

24.6s

$0.0310

65%

DeepSeek V4 Pro

by DeepSeek on OpenRouter

16.1s

$0.0196

65%

Model	Duration	Cost	Score
GPT-5.5 by OpenAI on OpenRouter	5.6s	$0.0525	100%
Gemini 2.5 Pro by Google on OpenRouter	15.3s	$0.1209	90%
Claude Opus 4.6 by Anthropic on OpenRouter	3.6s	$0.0220	79%
Claude Sonnet 4.6 by Anthropic on OpenRouter	2.8s	$0.0109	77%
Llama 4 Scout by Meta on OpenRouter	1.1s	$0.0003	76%
Llama 3.3 70B Instruct by Meta on OpenRouter	3.1s	$0.0003	74%
gpt-oss-20b by OpenAI on OpenRouter	4.2s	$0.0005	73%
Claude Opus 4.7 by Anthropic on OpenRouter	3.3s	$0.0285	70%
GLM 5.1 by Z.ai on OpenRouter	24.6s	$0.0310	65%
DeepSeek V4 Pro by DeepSeek on OpenRouter	16.1s	$0.0196	65%

Value Analysis

Find models with the best balance of quality, cost, and speed.

Best value frontier

Best value

Size = duration

Highlighted models offer the best score at their price point. Larger dots take longer to produce a result.

Token Usage

Average tokens used per model across all prompts.

Hy3 previewOpenRouter

2,215 avg (116 in / 2,099 out)

GLM 4.7OpenRouter

1,892 avg (108 in / 1,784 out)

GLM 4.7 FlashOpenRouter

1,693 avg (106 in / 1,587 out)

Qwen3.6 PlusOpenRouter

1,588 avg (118 in / 1,470 out)

Qwen3.6 FlashOpenRouter

1,529 avg (119 in / 1,410 out)