SOLAR-10.7B-v1.0 — benchmark results
Upstage's Apache-2.0 10.7B pretrained base model (December 2023), built by depth up-scaling Mistral-7B weights on a Llama-2 architecture. Provider: Upstage. Released 2023-12-11. Access: Open.
Unified ELO 1418 ± 11, rank #1139 of 1776 rated models, from 321 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Romanian NLU - MultiWikiQA RO | 77.57 | Reading comprehension Score (%) | 99.5 |
| EuroEval Portuguese NLU - MultiWikiQA PT | 79.82 | Reading comprehension Score (%) | 99.3 |
| EuroEval Italian NLU - SQuAD IT | 77.48 | Reading comprehension Score (%) | 98.8 |
| EuroEval Catalan NLU - MultiWikiQA CA | 78.2 | Reading comprehension Score (%) | 98.6 |
| EuroEval Danish NLU - Multi Wiki QA DA | 82.34 | Reading comprehension Score (%) | 98.5 |
| EuroEval Spanish NLU - MLQA ES | 70.14 | Reading comprehension Score (%) | 98.5 |
| EuroEval Bulgarian NLU - MultiWikiQA BG | 79.17 | Reading comprehension Score (%) | 97.6 |
| EuroEval Slovak NLU - Multi Wiki QA SK | 73.95 | Reading comprehension Score (%) | 97.5 |
| EuroEval Polish NLU - PoQuAD | 63.61 | Reading comprehension Score (%) | 97 |
| EuroEval Swedish NLU - Multi Wiki QA SV | 80.55 | Reading comprehension Score (%) | 96.4 |
| EuroEval Slovene NLU - MultiWikiQA SL | 72.15 | Reading comprehension Score (%) | 96.1 |
| EuroEval Hungarian NLU - MultiWikiQA HU | 69.79 | Reading comprehension Score (%) | 96 |
Interactive version: theaggregate.ai/model?slug=solar-10-7b-v1-0 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.