Model Comparison

Reka Flash (Sep '24)
vs. Sonar

Comparing 2 AI models · 7 benchmarks · Reka AI, Perplexity

Recommended Pick

Perplexity logo Sonar 7 metric wins

Strongest on: Input price, Output price, TTFT

Lowest Price

Perplexity logo

Sonar

$0.00/1M input price

Best Reasoning

Perplexity logo

Sonar

40.0 reasoning score

Blends available reasoning benchmarks

Composite Indices

Higher is better; speed and price are normalized

Standard Benchmarks

Only benchmarks with data are shown

Differences That Matter

Price gap

Sonar is ∞x cheaper on input tokens than Reka Flash (Sep '24).

Reasoning gap

Sonar leads Reka Flash (Sep '24) by 7.6 points on reasoning.

Top-pick rationale

Sonar wins 7 measurable categories, including Input price, Output price, TTFT, Latency.

Live compare

Response Face-Off

Run one prompt through the selected models and compare response quality with live speed and cost context.

Reka AI logo

Reka Flash (Sep '24)

Reka AI

Waiting

TTFT

Time

tok/s

Tokens

Cost

Waiting
Perplexity logo

Sonar

Perplexity

Waiting

TTFT

Time

tok/s

Tokens

Cost

Waiting

Which answer was more useful?

AI Chat

Chat with 80+ models

Inference API

EU-hosted inference

Full Comparison

Metric
Reka AI logo Reka Flash (Sep '24)
Reka AI
Top Pick
Perplexity logo Sonar
Perplexity
Pricing per 1M tokens
Input Cost $0.20/1M$0.00/1M
Output Cost $0.80/1M$0.00/1M
Blended (3:1) $0.35/1M
Specifications
Organization Reka AIPerplexity
Release Date Oct 4, 2024Jan 21, 2025
Performance & Speed
Throughput 85.8 tok/s
TTFT 1779ms
Latency 1779ms
Composite Indices
Value Score 100.0
Reasoning Score 32.440.0
Intelligence 12.015.5
Standard Benchmarks
GPQA 47.1%
MMLU Pro 68.9%
HLE 7.3%
LiveCodeBench 29.5%
MATH 500 52.9%81.7%
AIME (Original) 48.7%
SciCode 22.9%

Key Takeaways

Sonar offers the best value at $0.00/1M, making it ideal for high-volume applications and cost-conscious projects.

Sonar has the strongest reasoning profile with a 40.0 reasoning score, combining the available reasoning-heavy benchmarks.

All models support context windows of ∞+ tokens, suitable for processing lengthy documents and maintaining extended conversations.

When to Choose Each Model

Reka AI logo

Reka Flash (Sep '24)

  • General-purpose AI
  • Versatile applications
Perplexity logo

Sonar

  • Cost-sensitive applications
  • High-volume processing
  • Complex reasoning tasks
  • Research & analysis