Skip to main content

Compare Leaderboards Agents Insights

Loading...

Compare LLM models by quality, speed, and price. Find the right model for your use case.

Product

Explore Models
Compare
Leaderboards
LLM Selector
Cost Calculator
Provider Finder

Resources

Insights
FAQ
About
Methodology

Data Sources

Data from Artificial Analysis, OpenRouter, HuggingFace, and other public sources.

© 2026 FindLLM. All rights reserved.

Apriel-v1.5-15B-Thinker — ServiceNow | FindLLM

Home
Explore
Apriel-v1.5-15B-Thinker

Back to Explore

Apriel-v1.5-15B-Thinker

ServiceNow·Released 2025-09-30

Related Models

Apriel-v1.6-15B-Thinker2025-11-25

Performance

151

tokens/sec

Faster than 78% of models

0.19

seconds

Faster than 100% of models

13.46

seconds

Faster than 34% of models

Market Median

86 tok/s

75% faster

Median TTFT

1.07s

83% faster

Speed Comparison

OpenAI: GPT-5.4 Nano

152 tok/s+1%

Mistral Small (Feb '24)

152 tok/s+1%

Mistral Small (Sep '24)

152 tok/s+1%

Benchmarks

MMLU-Pro

77.3%

GPQA Diamond

71.3%

HLE

12.0%

LiveCodeBench

72.8%

SciCode

34.8%

TerminalBench Hard

10.6%

MATH-500Not evaluated

AIMENot evaluated

AIME 2025

87.5%

IFBench

61.7%

Long Context Recall

20.0%

Tau2

68.4%

Market AverageTop Score

Quick Compare

Similar Models

Qwen: Qwen3 Coder Next

Alibaba

Q: 28.3$0.28/1M262K ctx

DeepSeek V3.2 Exp (Non-reasoning)

DeepSeek

Q: 28.4$0.31/1M

Slower: 47%Coding: +11.3

Nemotron Cascade 2 30B A3B

NVIDIA

DeepSeek: DeepSeek V3.1 Terminus

DeepSeek

Q: 28.5$0.44/1M164K ctx

DeepSeek V3.1 (Non-reasoning)

DeepSeek

Q: 28.1$0.83/1M

Nova 2.0 Omni (medium)

Amazon

Q: 28.0$0.85/1M

Compare all 7 models

Quality Index

28.3

162nd of 507

Top 32%

Coding Index

18.7

210th of 417

Top 50%

Math Index

87.5

42nd of 269

Top 16%

Speed

151 tok/s

Top 22%

TTFT

0.19s

Market Position

Apriel-v1.5-15B-ThinkerMarket Average