Codesota · Models · BLT-Entropy 8B4 results · 4 benchmarks
Model card
BLT-Entropy 8B.
unknown
§ 02 · Benchmarks
Every benchmark BLT-Entropy 8B has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | HumanEval+ | Computer Code · Code Generation | pass-1 | 35.4% | #8 | — | source ↗ |
| 02 | MBPP+ | Computer Code · Code Generation | pass-1 | 41.8% | #8 | — | source ↗ |
| 03 | HellaSwag | Reasoning · Commonsense Reasoning | accuracy | 80.6% | #10 | — | source ↗ |
| 04 | MMLU | Reasoning · Commonsense Reasoning | accuracy | 57.4% | #61 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area
Where BLT-Entropy 8B actually performs.
§ 04 · Papers
1 paper with results for BLT-Entropy 8B.
- 2024-12-13· 4 results
Byte Latent Transformer: Patches Scale Better Than Tokens
§ 06 · Sources & freshness
Where these numbers come from.
pwc-dump
4
results
0 of 4 rows marked verified.