Cerebras-GPT-111M: benchmark results
Provider: Cerebras. Access: Open.
Unified ELO 1191 ± 22, rank #2914 of 2928 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 46.31 | MC2 (%) (0-shot) | 34 |
| Open Portuguese LLM - FaQuAD NLI | 43.97 | Macro F1 (%) | 17.1 |
| Open Portuguese LLM - ENEM | 19.66 | Accuracy (%) | 10.8 |
| Open Portuguese LLM - OAB Exams | 23.23 | Accuracy (%) | 9.4 |
| Open LLM Leaderboard v1 - MMLU | 25.51 | Accuracy (%) (5-shot) | 8.6 |
| Open Portuguese LLM - BLUEX | 18.08 | Accuracy (%) | 5.7 |
| Open Portuguese LLM - ASSIN2 RTE | 33.33 | Macro F1 (%) | 4.9 |
| Open LLM Leaderboard v1 - GSM8K | 0 | Accuracy (%) (5-shot) | 4.6 |
| Open LLM Leaderboard v1 - HellaSwag | 26.73 | Normalized accuracy (%) (10-shot) | 3.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 20.22 | Normalized accuracy (%) (25-shot) | 0.1 |
| Open LLM Leaderboard v1 - WinoGrande | 47.75 | Accuracy (%) (5-shot) | 0.1 |
Interactive version: theaggregate.ai/model?slug=cerebras-gpt-111m · How It Works · Data refreshed daily, snapshot 2026-09-23.