crawler-status-logs-v1
AI API Hunt
R

Ring-flash-2.0

Last updated: Recently

Model Type

Text

Max Context

-

Max Output

-

Parameter Scale

-

Ring flash 2.0 by InclusionAI: Text model; TTFT 1.521s, 86.6 tok/s.

Input Modality

-

Output Modality

-

Inference Speed

86.570 tokens/s

Latest Release Date

9/19/2025

SDK Ecosystem

-

artificial-analysismanufactureraa-bootstrap
Model Overview Fields

name

Ring-flash-2.0

Release date

9/19/2025

Performance

86.570 tokens/s

model_creator.name

InclusionAI

AA Evaluation Scores

AA Intelligence Index

14

AA Coding Index

10.6

AA Math Index

83.7

MMLU Pro

0.793

GPQA

0.725

HLE

0.089

LiveCodeBench

0.628

SciCode

0.168

Math-500

-

AIME

-

AIME 2025

0.837

IFBench

0.433

LCR

0.21

TerminalBench Hard

0.076

TAU2

0

Output Speed (tokens/s)

86.57 tok/s

TTFT (s)

1.521s

First Answer Token (s)

24.623s

Share:
Report / Feedback