whatmodel.sh / Sonar Reasoning Pro

Sonar Reasoning Pro

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Sonar Reasoning Pro is a closed-weights language model from Perplexity.

Catalogue identity notes

Comparison-only. Arena entry 'ppl-sonar-reasoning-pro-high' (search). Perplexity API system (search-augmented reasoning). Arena entry = sonar-reasoning-pro with high search context size. Sonar supported until September 27, 2026 (Perplexity docs).

62.2±4.9comparison only: no current run option verifiedfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of Sonar Reasoning Pro, out of 1132 with a score, then more from Perplexity.

#modelscorewhereRAMreleased
241GPT-4.1 OpenAI62±1api $3.50/M2025-04
242Nemotron 3.5 Lightning 30B-A3B NVIDIA62±2api $0.087/M +local~20GB2026-08
243Sonar Reasoning Pro Perplexity62±5comparison only
244GLM-4.6V Z.ai62±2api $0.45/M +local~51GB2025-12
245Devstral 2 (2512) Mistral62±2local~75GB2025-12
more from Perplexity
229Sonar Pro Perplexity63±5comparison only2025-01

see all LLMs · find the ones that fit your machine

$ what it's good at

web search▂▁▂▇▅█▃▄▁▂▁▁ #74 of 96 * · 89% of its score · 1 test

Beats DeepSeek V4 Flash (Preview, Apr 2026), Grok 4.3, Nemotron 3 Ultra 550B-A55B here, though they rank higher overall. Trails GPT-4o mini (2024-07-18), Mistral Small 3.1 24B (2503), Llama 4 Scout (109B-A17B) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Arena search systems (style controlled)1138.1 ✎▁·▁▃▂▂▂█▅▂▁▁ beats 2/30avg 1055▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 89%blunt

$ where to run it

No verified API or download recorded yet · add one

$ how the score was worked out · LMArena leaderboard dataset 89%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
LMArena leaderboard dataset1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 89%CC BY 4.0
prior · pull toward the middle▇▇▇ 11%
weighted average= 62.2

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json