🇺🇸Reka AIOpen source

Reka Flash 3.

See how Reka Flash 3 compares with other broadly useful AI models across quality, speed, price, context, and practical capabilities.

CompareVisit model

Quality

#61/67

0

Overall quality score

Speed

#66/67

—

Output tokens per second

Input price

#17/67

$0.10/1M

Per 1M tokens

Output price

#10/67

$0.20/1M

Per 1M tokens

Context

#65/67

65.5K

Content read at once

Comparison summary

Reka Flash 3 ranks #61 of 67 for overall quality and #66 for response speed in the current catalogue.

Its listed input price is $0.10/1M, output price is $0.20/1M, and it can work with up to 65.5K of context at once.

Its strongest areas in the current data are everyday help, coding, complex tasks.

Practical specifications

Company
Reka AI
Reasoning
Yes
Open weights
Yes
Input
Text
Output
Text
Context window
65.5K

Reka Flash 3 technical benchmarks.

Named evaluation records for technical comparison. Results retain their original benchmark names and sources.

BenchmarkAreaReka Flash 3Source
GPQAGPQA Diamond52.9OpenRouter model benchmarks
Humanity's Last ExamHLE5.1OpenRouter model benchmarks
IFBenchIFBench30.4OpenRouter model benchmarks
τ²-Bench Telecomτ²-Bench Telecom0OpenRouter model benchmarks
AA-LCRAA-LCR0OpenRouter model benchmarks
CritPtCritPt0OpenRouter model benchmarks
SciCodeSciCode26.7OpenRouter model benchmarks
Terminal-Bench HardTerminal-Bench Hard0OpenRouter model benchmarks
AA-Omniscience AccuracyAA-Omniscience Accuracy13.4OpenRouter model benchmarks
AA-Omniscience Non-Hallucination RateAA-Omniscience Non-Hallucination Rate9.9OpenRouter model benchmarks

Quality benchmarks

See where Reka Flash 3 stands.

The darker bar marks Reka Flash 3; the lighter bars provide context from other leading models.

Highlights

Quality

Overall capability · Higher is better

Speed

Output tokens per second · Higher is better

Input price

USD per 1M tokens · Lower is better