NOUMENOpen app
NOUMEN

reka · Open weights

Reka Flash 3

Added Oct 15, 2026Open weights

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

Reka's 21B reasoning model for chat and coding, served directly by Reka.

  • Reasoning
  • Structured output
Input
Text
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.11
Output
$0.21

Reference prices as published by the model provider. API example

Specifications

Context window
65.5K
Max output
65.5K
Average output (7 days)
2.7K tokens
Longer than 95% of 465 models

Side by side

Reka Flash 3 compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Reka Flash 3rekaThis modelMinistral 8BMistralRemove
ProviderrekaMistral
Discovery tierOpen weightsOpen weights
AddedOct 15, 2026Dec 4, 2025
Limits
Context window65.54K262.14KBest
Max output65.54KBest32.77K
Average output2.7K tokens40 tokens
Pricing, USD per 1M tokens
Input$0.11Best$0.15
Output$0.21$0.15Best
Performance
Request success (24h)—100.0%
Benchmark indexes
Intelligence Index5.6Best5.5
Coding Index—9.7
Math Index33.7Best31.7
Capabilities
ReasoningYesNo
Structured outputYesNo
Reasoning effort——

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

  • Reka Flash 3
  • Ministral 8B

Intelligence Index

  • Reka Flash 35.6
  • Ministral 8B5.5

Reka Flash 3: Better than 2% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Reka Flash 3: —
    • Ministral 8B: 9.7

  • Math Index

    Composite of the math evaluations

    • Reka Flash 3: 33.7Top
    • Ministral 8B: 31.7

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Reka Flash 3: —
    • Ministral 8B: 0.5%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Reka Flash 3: —
    • Ministral 8B: 0.0%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Reka Flash 3: —
    • Ministral 8B: 77 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Reka Flash 3: —
    • Ministral 8B: 213 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Reka Flash 3: —
    • Ministral 8B: 0.8%

  • AA-LCRv1.1

    Reasoning across long documents

    • Reka Flash 3: 0.0%
    • Ministral 8B: 25.7%Top

  • MLCR-AA

    Long-context reasoning over medical records

    • Reka Flash 3: —
    • Ministral 8B: 0.0%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Reka Flash 3: 4.4%Top
    • Ministral 8B: 4.3%

  • GPQA Diamond

    Graduate-level science questions

    • Reka Flash 3: 52.9%Top
    • Ministral 8B: 47.1%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Reka Flash 3: 66.9%Top
    • Ministral 8B: 64.2%

  • IFBench

    Following precise output instructions

    • Reka Flash 3: 30.4%Top
    • Ministral 8B: 29.1%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Reka Flash 3: —
    • Ministral 8B: 0.0%

  • SciCode

    Scientific computing in Python

    • Reka Flash 3: —
    • Ministral 8B: 20.7%

  • LiveCodeBench

    Recent competitive programming problems

    • Reka Flash 3: 43.5%Top
    • Ministral 8B: 30.3%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Reka Flash 3: 33.7%Top
    • Ministral 8B: 31.7%

  • AIME

    Competition mathematics

    • Reka Flash 3: 51.0%
    • Ministral 8B: —

  • MATH-500

    Competition math problems

    • Reka Flash 3: 89.3%
    • Ministral 8B: —

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Reka Flash 3: 0.0%
    • Ministral 8B: 4.5%Top

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Reka Flash 3: 0.0%
    • Ministral 8B: 26.6%Top

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Reka Flash 3: 0.0%
    • Ministral 8B: 25.7%Top

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "reka/reka-flash-3",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="reka/reka-flash-3",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

reka

Other reka models, starting with the same family.