Babel-83B-Chat: benchmark results
Provider: Other.
Aggregate Rating 1553 ± 36, rank #1670 of 10916 rated models, from 28 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| FilBench - Cultural Knowledge | 75.21 | Category Score (%) | 94.6 |
| FilBench | 60.85 | FilBench Score (%) | 83.3 |
| FilBench - Classical NLP | 88.81 | Category Score (%) | 80.6 |
| FilBench - Reading Comprehension | 64.85 | Category Score (%) | 78.4 |
| SAHARA - General Knowledge | 59.81 | Accuracy (%) | 68.1 |
| SAHARA - POS Tagging | 20.76 | Macro-F1 (%) | 68.1 |
| FilBench - Generation | 14.53 | Category Score (%) | 66.7 |
| SAHARA - Token-Level Cluster | 17.31 | Cluster score (mean of task scores) | 59.6 |
| SAHARA - Language Identification | 3.05 | Macro-F1 (%) | 57.4 |
| SAHARA - Topic Classification | 52.09 | Macro-F1 (%) | 57.4 |
| SAHARA - Summarization | 15.46 | ROUGE-L | 55.3 |
| SAHARA - Reading Comprehension | 30.83 | Accuracy (%) | 51.1 |
Interactive version: theaggregate.ai/model?slug=babel-83b-chat · How It Works · Data refreshed daily, snapshot 2026-11-08.