perplexity: perplexity-decider-v1.2
1 benchmarks
Leaderboard position
#282
Overall rank (of 1122 models)
1613
Elo rating
1
Benchmarks
Top 25.1%
Percentile
In perplexity (of 7 models)
Above: inclusionAI: ui-venus-1.5-30b-a3b #281
Below: skywork-ai: skyreels-v4 #283
Benchmark highlights
Best benchmark
Decision Index v0.4.1
68
Worst benchmark
Decision Index v0.4.1
68
Nearest competitor from another company
The model from another company with the most similar benchmark scores.
appeared as nearest in 1 of 1 benchmarks
1/1
100.0%
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 | ~99.2 | 50% | — |
| AIME 2025 | ~91.13 | 50% | — |
| AIME 2026 | ~88.22 | 50% | — |
| HMMT Feb 2026 | ~79.8 | 50% | — |
| GPQA Diamond | ~74.83 | 50% | — |
| MMLU-Pro | ~79.91 | 50% | — |
| Humanity's Last Exam (no tools) | ~25.17 | 50% | — |
| IFEval | ~92.67 | 50% | — |
| IFBench | ~65.94 | 50% | — |
| HumanEval | ~95.77 | 50% | — |
| MBPP | ~93.7 | 50% | — |
| Terminal-Bench v2.1 | ~47.77 | 50% | — |
| MMLU | ~87.27 | 50% | — |
| SWE-bench Verified | ~62.99 | 50% | — |
| SWE-bench Pro | ~40.36 | 50% | — |
| SciCode | ~38.77 | 50% | — |
| AA-LCR | ~57.95 | 50% | — |
| Humanity's Last Exam (with tools) | ~33.91 | 50% | — |
| GSM8K | ~99.6 | 50% | — |
| -(CoderPPL) | ~-1.69 | 50% | — |
| LiveCodeBench v6 | ~73.31 | 50% | — |
| MMMU-Pro | ~67.22 | 50% | — |
| MATH | ~92.68 | 50% | — |
| BBH | ~82.22 | 50% | — |