Quality
Highest overall scores
- 1
Perplexity: Sonar Pro0 - 2Perplexity: Sonar Pro Search0
- 3Perplexity: Sonar Reasoning Pro0
Perplexity model benchmarks.
Compare Perplexity models across answer quality, coding, complex tasks, speed, price, and context size.
Response speed
Fastest output in this sample
- 1Perplexity: Sonar Pro102 t/s
- 2Perplexity: Sonar Pro Search48 t/s
- 3Perplexity: Sonar Reasoning Pro7 t/s
Input price
Lowest price per 1M tokens
- 1Perplexity: Sonar Reasoning Pro$2.00/1M
- 2Perplexity: Sonar Pro$3.00/1M
- 3Perplexity: Sonar Pro Search$3.00/1M
Highlights
Quality
Overall capability · Higher is better
Speed
Output tokens per second · Higher is better
Input price
USD per 1M tokens · Lower is better
Quality benchmarks
Compare Perplexity model capability.
Performance and price
Compare practical tradeoffs.
All Perplexity models.
3 models in the current catalogue.
| Model | Links | |||||
|---|---|---|---|---|---|---|
| Perplexity: Sonar Pro | 0 | 102 t/s | 200K | $3.00 | $15.00 | |
| Perplexity: Sonar Pro Search | 0 | 48 t/s | 200K | $3.00 | $15.00 | |
| Perplexity: Sonar Reasoning Pro | 0 | 7 t/s | 128K | $2.00 | $8.00 |
Perplexity technical benchmarks.
Compare named evaluation records available for Perplexity models. Missing results remain blank rather than being estimated.
| Benchmark | Area | Sonar Pro | Sonar Pro Search | Sonar Reasoning Pro | Source |
|---|---|---|---|---|---|
| GPQA | GPQA Diamond | 57.8 | — | — | OpenRouter model benchmarks |
| Humanity's Last Exam | HLE | 6.6 | — | — | OpenRouter model benchmarks |
| SciCode | SciCode | 22.6 | — | — | OpenRouter model benchmarks |