TemptressTensor-10.7B-v0.1a: benchmark results
jsfs11 release made by a passthrough merge of overlapping layer slices from jsfs11/RandomMergeNoNormWEIGHTED-7B-DARETIES. The published slice recipe and configuration both specify 48 decoder layers, preserving its depth-expanded identity. Provider: jsfs11. Access: Open.
Aggregate Rating 1449 ± 38, rank #3811 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 88.26 | Normalized accuracy (%) (10-shot) | 90.5 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 70.21 | MC2 (%) (0-shot) | 90.1 |
| Open LLM Leaderboard v1 - ARC Challenge | 70.99 | Normalized accuracy (%) (25-shot) | 87.5 |
| Open LLM Leaderboard v1 - WinoGrande | 82.79 | Accuracy (%) (5-shot) | 85.6 |
| Open LLM Leaderboard v1 - MMLU | 64.53 | Accuracy (%) (5-shot) | 72.1 |
| Open LLM Leaderboard v1 - GSM8K | 52.24 | Accuracy (%) (5-shot) | 64.1 |
Interactive version: theaggregate.ai/model?slug=temptresstensor-10-7b-v0-1a · How It Works · Data refreshed daily, snapshot 2026-11-08.