nullsilver: alpha-sys-1-1.6b
1 benchmarks
Leaderboard position
#657
Overall rank (of 1121 models)
753
Elo rating
1
Benchmarks
Top 58.6%
Percentile
In nullsilver (of 3 models)
Above: Microsoft: azure-hd-2.5 #656
Below: Z.ai: glm-asr-nano-2512 #658
Benchmark highlights
Best benchmark
CIFAR-10
92.2
Worst benchmark
CIFAR-10
92.2
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 | ~84.62 | 50% | — |
| AIME 2025 | ~62.77 | 50% | — |
| AIME 2026 | ~71.53 | 50% | — |
| HMMT Feb 2026 | ~63.04 | 50% | — |
| GPQA Diamond | ~55.85 | 50% | — |
| MMLU-Pro | ~58.73 | 50% | — |
| Humanity's Last Exam (no tools) | ~9.83 | 50% | — |
| IFEval | ~80.89 | 50% | — |
| IFBench | ~51.66 | 50% | — |
| HumanEval | ~70.76 | 50% | — |
| MBPP | ~73.18 | 50% | — |
| Terminal-Bench v2.1 | ~17.99 | 50% | — |
| MMLU | ~65.06 | 50% | — |
| SWE-bench Verified | ~36.01 | 50% | — |
| SWE-bench Pro | ~15.17 | 50% | — |
| SciCode | ~25.34 | 50% | — |
| AA-LCR | ~41.12 | 50% | — |
| Artificial Analysis Intelligence Index v5.0.1 | ~12 | 50% | — |
| Humanity's Last Exam (with tools) | ~13.44 | 50% | — |
| GSM8K | ~79.01 | 50% | — |
| -(CoderPPL) | ~-1.69 | 50% | — |
| LiveCodeBench v6 | ~53.61 | 50% | — |
| MMMU-Pro | ~51.05 | 50% | — |
| MATH | ~56.5 | 50% | — |
| BBH | ~63.08 | 50% | — |