deepslate: opal
1 benchmarks
Leaderboard position
#692
Overall rank (of 1121 models)
679
Elo rating
1
Benchmarks
Top 61.7%
Percentile
In deepslate (of 1 models)
Above: perplexity: sonar-pro #691
Below: fish-audio: fish-audio-s2-pro #693
Benchmark highlights
Best benchmark
Artificial Analysis: Speech Reasoning (Big Bench Audio)
59.1
Worst benchmark
Artificial Analysis: Speech Reasoning (Big Bench Audio)
59.1
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 | ~83.34 | 50% | — |
| AIME 2025 | ~60.35 | 50% | — |
| AIME 2026 | ~70.1 | 50% | — |
| HMMT Feb 2026 | ~61.6 | 50% | — |
| GPQA Diamond | ~54.22 | 50% | — |
| MMLU-Pro | ~56.92 | 50% | — |
| Humanity's Last Exam (no tools) | ~8.51 | 50% | — |
| IFEval | ~79.88 | 50% | — |
| IFBench | ~50.43 | 50% | — |
| HumanEval | ~68.62 | 50% | — |
| MBPP | ~70.37 | 50% | — |
| Terminal-Bench v2.1 | ~15.42 | 50% | — |
| MMLU | ~63.15 | 50% | — |
| SWE-bench Verified | ~33.69 | 50% | — |
| SWE-bench Pro | ~13 | 50% | — |
| SciCode | ~24.18 | 50% | — |
| AA-LCR | ~39.67 | 50% | — |
| Artificial Analysis Intelligence Index v5.0.1 | ~12 | 50% | — |
| Humanity's Last Exam (with tools) | ~11.9 | 50% | — |
| GSM8K | ~76.22 | 50% | — |
| -(CoderPPL) | ~-2.01 | 50% | — |
| LiveCodeBench v6 | ~51.92 | 50% | — |
| MMMU-Pro | ~49.66 | 50% | — |
| MATH | ~53.4 | 50% | — |
| BBH | ~61.44 | 50% | — |