GPTNeo350M-Instruct-SFT: benchmark results
Provider: OpenAI. Access: API.
Aggregate Rating 1107 ± 40, rank #10634 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 45.25 | MC2 (%) (0-shot) | 30.2 |
| Open LLM Leaderboard v1 - GSM8K | 0.3 | Accuracy (%) (5-shot) | 11.4 |
| Open LLM Leaderboard v1 - MMLU | 25.76 | Accuracy (%) (5-shot) | 9.7 |
| Open LLM Leaderboard v1 - HellaSwag | 38.55 | Normalized accuracy (%) (10-shot) | 7.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 25.94 | Normalized accuracy (%) (25-shot) | 5.3 |
| Open LLM Leaderboard v1 - WinoGrande | 50.2 | Accuracy (%) (5-shot) | 3 |
Interactive version: theaggregate.ai/model?slug=gptneo350m-instruct-sft · How It Works · Data refreshed daily, snapshot 2026-11-08.