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.

Tiny Aya Global — Cohere | FindLLM

Home
Explore
Tiny Aya Global

Back to Explore

Tiny Aya Global

Cohere·Released 2026-02-17

Open Source

Performance

125

tokens/sec

Faster than 69% of models

0.27

seconds

Faster than 97% of models

0.27

seconds

Faster than 98% of models

Market Median

86 tok/s

46% faster

Median TTFT

1.07s

75% faster

Speed Comparison

Qwen: Qwen3 VL 30B A3B Instruct

124 tok/s-1%

NVIDIA Nemotron Nano 9B V2 (Reasoning)

124 tok/s-1%

Qwen3 VL 30B A3B (Reasoning)

126 tok/s+1%

Benchmarks

MMLU-ProNot evaluated

GPQA Diamond

30.5%

HLE

5.2%

LiveCodeBenchNot evaluated

SciCode

3.6%

TerminalBench Hard

0.0%

MATH-500Not evaluated

AIMENot evaluated

AIME 2025Not evaluated

IFBench

20.1%

Long Context Recall

0.0%

Tau2

0.0%

Market AverageTop Score

Open Source

Quick Compare

Similar Models

Gemma 3n E2B Instruct

Google

Granite 4.0 H 350M

IBM

Gemma 3 1B Instruct

Google

Qwen3 0.6B (Non-reasoning)

Alibaba

Apertus 8B Instruct

Swiss AI Initiative

Granite 4.0 350M

IBM

Compare all 7 models

Quality Index

4.7

507th of 507

Coding Index

1.2

404th of 417

Top 97%

Speed

125 tok/s

Top 31%

TTFT

0.27s

Market Position

Tiny Aya GlobalMarket Average