perplexity: perplexity-decider-flash-v1.2
1 benchmarks
Leaderboard position
#526
Overall rank (of 1121 models)
1041
Elo rating
1
Benchmarks
Top 46.9%
Percentile
In perplexity (of 7 models)
Above: farleyknight-org-username: vit-base-mnist #525
Below: SpaceXAI: Grok 3 #527
Benchmark highlights
Best benchmark
Decision Index v0.4.1
54.3
Worst benchmark
Decision Index v0.4.1
54.3
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 |
|---|---|---|---|
| MATH-500 | ~89.62 | 50% | — |
| AIME 2025 | ~72.22 | 50% | — |
| AIME 2026 | ~77.1 | 50% | — |
| HMMT Feb 2026 | ~68.63 | 50% | — |
| GPQA Diamond | ~62.19 | 50% | — |
| MMLU-Pro | ~65.8 | 50% | — |
| Humanity's Last Exam (no tools) | ~14.96 | 50% | — |
| IFEval | ~84.83 | 50% | — |
| IFBench | ~56.42 | 50% | — |
| HumanEval | ~79.13 | 50% | — |
| MBPP | ~84.13 | 50% | — |
| Terminal-Bench v2.1 | ~27.97 | 50% | — |
| MMLU | ~72.48 | 50% | — |
| SWE-bench Verified | ~45.05 | 50% | — |
| SWE-bench Pro | ~23.59 | 50% | — |
| SciCode | ~29.84 | 50% | — |
| AA-LCR | ~46.74 | 50% | — |
| Artificial Analysis Intelligence Index v5.0.1 | ~12 | 50% | — |
| Humanity's Last Exam (with tools) | ~20.29 | 50% | — |
| GSM8K | ~89.84 | 50% | — |
| -(CoderPPL) | ~-1.69 | 50% | — |
| LiveCodeBench v6 | ~60.19 | 50% | — |
| MMMU-Pro | ~56.46 | 50% | — |
| MATH | ~68.59 | 50% | — |
| BBH | ~69.47 | 50% | — |