Toolbit.aiToolbit.ai

Find, compare, and explore the best AI tools to match your specific tasks and use cases.

Explore

  • AI Search
  • Compare ToolsNew
  • Browse Categories
  • Trending Tools
  • Most Popular
  • New Additions

Resources

  • Updates HubNew
  • AI News
  • ModelsNew
  • Blog Articles
  • NewsletterNew

Company

  • Launch a Tool
  • Advertise with Us
  • Guest Post
  • Contact Us
© 2026 Toolbit.ai. All rights reserved.
Privacy PolicyTerms & ConditionsDisclaimer
There's An AI For That favicon
There's An AI For That•The front page of AI for everyone
Toolbit.ai
Toolbit.ai
UpdatesNew
Blog
Toolbit.ai
Toolbit.ai
Toolbit.ai
Toolbit.ai
UpdatesNew
Blog
Sign in
  1. Home
  2. Updates
  3. Models
  4. Reka Flash 3
Reka AI
Released March 10, 2025Cutoff January 2025

Reka Flash 3

Reka Flash 3 by Reka is a 21B reasoning model with 66K context, explicit reasoning tags, budget forcing, and function calling for compact deployments.

Visit Reka AIAnnouncement
Inputs
Text
Outputs
Text

Model Overview

Capabilities, design details, and architectural traits

Reka Flash 3 - Compact reasoning model

Reka Flash 3 is Reka’s 21B-parameter reasoning model for compact deployments, with documentation emphasizing explicit reasoning traces, function calling, and a long but practical context window.

Defining Characteristics

  • 21B parameter reasoning model: Reka describes Flash 3 as a 21-billion-parameter model trained from scratch for general-purpose reasoning.
  • Explicit reasoning tags: The model uses <reasoning> tags to expose internal thought traces in supported integrations.
  • Budget forcing for latency control: Provider documentation says Flash 3 supports a budget forcing mechanism to cap reasoning steps and control latency.
  • 66K context window: Public listings document a 65,536/66K-token context window and matching maximum output size.

Core Design

  • The model is text-first and English-focused in the official model card, with on-device or low-latency deployment called out as a key use case.
  • Reka also positions Flash 3 as suitable for function calling, coding, and instruction following.

Benchmark Performance

Independent evaluations · Artificial Analysis

3.7%
Intelligence

Accuracy & Capability Details

GPQA - Graduate Science52.9%
Humanity's Last Exam4.4%
SciCode - Scientific Coding26.7%
Instruction Following30.4%
Long Context Reasoning0.0%
τ²-Bench - Agentic Tasks0.0%
TerminalBench - System Control0.0%
Specs
Context window
66Ktokens
Input pricing
$0.20per 1M tokens
Output pricing
$0.80per 1M tokens

Prices in USD.

Compare Models Side-by-Side

Evaluate specifications, pricing, and independent benchmark indices

Model Details
General Info
ProviderReka AIAnthropicAnthropic
Release DateMarch 10, 2025July 24, 2026June 9, 2026
Knowledge CutoffJan 2025May 2026-
Context & Limits
Context Window66K
1M
Best Context Window
1M
Best Context Window
Pricing (per 1M tokens)
Input Pricing
$0.20
Best Input Pricing
$5$10
Output Pricing
$0.80
Best Output Pricing
$25$50
Modalities
Inputs
text
textimage
textimagefile
Outputs
text
text
text
Benchmarks (0-100)
Intelligence Index3.7
63.1
Best Intelligence Index
62.1
Coding Index-
78.0
Best Coding Index
76.5
Agentic Index-
59.2
Best Agentic Index
56.6
Reka Flash 3
Claude Opus 5
Claude Fable 5

GPQA Benchmark

Graduate-level reasoning and expert Q&A evaluation.

53%
Reka Flash 3
GPQA Benchmark
Score: 53%
Reka Flash 3
93%
Claude Opus 5
GPQA Benchmark
Score: 93%
Claude Opus 5
93%
Claude Fable 5
GPQA Benchmark
Score: 93%
Claude Fable 5

Humanity's Last Exam

Extremely difficult logical reasoning and knowledge.

4%
Reka Flash 3
Humanity's Last Exam
Score: 4%
Reka Flash 3
55%
Claude Opus 5
Humanity's Last Exam
Score: 55%
Claude Opus 5
56%
Claude Fable 5
Humanity's Last Exam
Score: 56%
Claude Fable 5

Long Context Reasoning

Logical reasoning over long context windows.

0%
Reka Flash 3
Long Context Reasoning
Score: 0%
Reka Flash 3
76%
Claude Opus 5
Long Context Reasoning
Score: 76%
Claude Opus 5
77%
Claude Fable 5
Long Context Reasoning
Score: 77%
Claude Fable 5

Independent evaluation data provided by Artificial Analysis. To view the latest benchmarks and full details, visit their official site.

Back to all models