nullsilver: alpha-sys-1-450m
1 benchmarks
Leaderboard position
#920
Overall rank (of 1121 models)
156
Elo rating
1
Benchmarks
Top 82.1%
Percentile
In nullsilver (of 3 models)
Above: tfjiangxilab: tianjiangzhuge_3b #919
Below: Apple: openelm-1_1b-instruct #921
Benchmark highlights
Best benchmark
CIFAR-10
85.1
Worst benchmark
CIFAR-10
85.1
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 | ~74.27 | 50% | — |
| AIME 2025 | ~43.19 | 50% | — |
| AIME 2026 | ~59.99 | 50% | — |
| HMMT Feb 2026 | ~51.45 | 50% | — |
| GPQA Diamond | ~42.72 | 50% | — |
| MMLU-Pro | ~44.09 | 50% | — |
| Humanity's Last Exam (no tools) | ~4 | 50% | — |
| IFEval | ~72.73 | 50% | — |
| IFBench | ~41.78 | 50% | — |
| HumanEval | ~53.43 | 50% | — |
| MBPP | ~50.47 | 50% | — |
| Terminal-Bench v2.1 | ~8.6 | 50% | — |
| MMLU | ~49.67 | 50% | — |
| SWE-bench Verified | ~17.28 | 50% | — |
| SWE-bench Pro | ~5.24 | 50% | — |
| SciCode | ~16.01 | 50% | — |
| AA-LCR | ~29.45 | 50% | — |
| Artificial Analysis Intelligence Index v5.0.1 | ~12 | 50% | — |
| Humanity's Last Exam (with tools) | ~11.9 | 50% | — |
| GSM8K | ~56.55 | 50% | — |
| -(CoderPPL) | ~-5.25 | 50% | — |
| LiveCodeBench v6 | ~39.98 | 50% | — |
| MMMU-Pro | ~39.84 | 50% | — |
| MATH | ~31.45 | 50% | — |
| BBH | ~49.83 | 50% | — |