perplexity: sonar-pro
2 benchmarks
Leaderboard position
#692
Overall rank (of 1122 models)
678
Elo rating
2
Benchmarks
Top 61.7%
Percentile
In perplexity (of 7 models)
Above: tiger-lab: general-reasoner-qwen3-4b #691
Below: deepslate: opal #693
Benchmark highlights
Nearest competitor from another company
The model from another company with the most similar benchmark scores.
appeared as nearest in 1 of 2 benchmarks
1/2
50.0%
| Model | Votes | % of benchmarks |
|---|---|---|
| Google: Gemma 4 E2B Instruct | 1 | 50.0% |
| Moonshot AI: kimi-linear-48b-a3b-instruct | 1 | 50.0% |
Benchmarks
Predicted scores
Estimated from 25 similar models and the global Elo rating. These are projections, not measured results.
| Benchmark | Predicted | Confidence | Based on |
|---|---|---|---|
| Artificial Analysis Intelligence Index v5.0.1 | ~12 | 50% | — |
| MATH-500 | ~83.35 | 50% | — |
| AIME 2025 | ~60.38 | 50% | — |
| AIME 2026 | ~70.13 | 50% | — |
| HMMT Feb 2026 | ~61.61 | 50% | — |
| GPQA Diamond | ~54.24 | 50% | — |
| MMLU-Pro | ~56.94 | 50% | — |
| Humanity's Last Exam (no tools) | ~8.47 | 50% | — |
| IFEval | ~79.89 | 50% | — |
| IFBench | ~50.45 | 50% | — |
| HumanEval | ~68.63 | 50% | — |
| MBPP | ~70.39 | 50% | — |
| Terminal-Bench v2.1 | ~15.11 | 50% | — |
| MMLU | ~63.17 | 50% | — |
| SWE-bench Verified | ~33.8 | 50% | — |
| SWE-bench Pro | ~13.07 | 50% | — |
| SciCode | ~24.1 | 50% | — |
| AA-LCR | ~39.62 | 50% | — |
| Humanity's Last Exam (with tools) | ~11.9 | 50% | — |
| GSM8K | ~76.25 | 50% | — |
| -(CoderPPL) | ~-2.01 | 50% | — |
| LiveCodeBench v6 | ~51.94 | 50% | — |
| MMMU-Pro | ~49.64 | 50% | — |
| MATH | ~53.43 | 50% | — |
| BBH | ~61.46 | 50% | — |