Niederstetten Benchmark

Jan 28, 2026

5 tasks

110 models

$0.5276

karllorey

Link only

ResultsPreliminary

Vote in the arena

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

Gemini 3 Flash Preview

by Google

1.6s

$0.0011

96%

score

Gemini 2.5 Pro

by Google

10.7s

$0.0484

96%

score

DeepSeek V3.2

by DeepSeek

6.6s

$0.0004

90%

score

Auto Router

by OpenRouter

6.2s

$0.0208

86%

score

DeepSeek V3.2 Speciale

by DeepSeek

41.5s

$0.0084

74%

score

Prompt Details

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

Model Comparison

Compare performance across models and prompts.

Gemini 3 Flash Preview

by Google on OpenRouter

1.6s

$0.0011

96%

Gemini 2.5 Pro

by Google on OpenRouter

10.7s

$0.0484

96%

DeepSeek V3.2

by DeepSeek on OpenRouter

6.6s

$0.0004

90%

Auto Router

by OpenRouter on OpenRouter

6.2s

$0.0208

86%

DeepSeek V3.2 Speciale

by DeepSeek on OpenRouter

41.5s

$0.0084

74%

Claude Opus 4.5

by Anthropic on OpenRouter

3.8s

$0.0141

74%

DeepSeek V3 0324

by DeepSeek on OpenRouter

8.4s

$0.0011

72%

Claude Sonnet 4.5

by Anthropic on OpenRouter

3.8s

$0.0102

68%

Mistral Large 3 2512

by Mistral on OpenRouter

3.9s

$0.0017

68%

GLM 4.7

by Z.ai on OpenRouter

15.9s

$0.0065

68%

Model	Duration	Cost	Score
Gemini 3 Flash Preview by Google on OpenRouter	1.6s	$0.0011	96%
Gemini 2.5 Pro by Google on OpenRouter	10.7s	$0.0484	96%
DeepSeek V3.2 by DeepSeek on OpenRouter	6.6s	$0.0004	90%
Auto Router by OpenRouter on OpenRouter	6.2s	$0.0208	86%
DeepSeek V3.2 Speciale by DeepSeek on OpenRouter	41.5s	$0.0084	74%
Claude Opus 4.5 by Anthropic on OpenRouter	3.8s	$0.0141	74%
DeepSeek V3 0324 by DeepSeek on OpenRouter	8.4s	$0.0011	72%
Claude Sonnet 4.5 by Anthropic on OpenRouter	3.8s	$0.0102	68%
Mistral Large 3 2512 by Mistral on OpenRouter	3.9s	$0.0017	68%
GLM 4.7 by Z.ai on OpenRouter	15.9s	$0.0065	68%

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.

GPT-5 NanoOpenRouter

1,594 avg (17 in / 1,577 out)

DeepSeek V3.2 SpecialeOpenRouter

1,403 avg (17 in / 1,386 out)

Gemini 2.5 ProOpenRouter

979 avg (12 in / 967 out)

gpt-oss-20bOpenRouter

894 avg (74 in / 820 out)

gpt-oss-120bOpenRouter

737 avg (74 in / 663 out)