gpt3-finnish-large: benchmark results
Provider: OpenAI. Access: API.
Aggregate Rating 1089 ± 42, rank #10830 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 44.35 | MC2 (%) (0-shot) | 26.9 |
| Open LLM Leaderboard v1 - HellaSwag | 32.88 | Normalized accuracy (%) (10-shot) | 6.8 |
| Open LLM Leaderboard v1 - WinoGrande | 51.54 | Accuracy (%) (5-shot) | 5.6 |
| Open LLM Leaderboard v1 - GSM8K | 0 | Accuracy (%) (5-shot) | 4.5 |
| Open LLM Leaderboard v1 - MMLU | 24.11 | Accuracy (%) (5-shot) | 3 |
| Open LLM Leaderboard v1 - ARC Challenge | 21.76 | Normalized accuracy (%) (25-shot) | 0.6 |
Interactive version: theaggregate.ai/model?slug=gpt3-finnish-large · How It Works · Data refreshed daily, snapshot 2026-11-08.