GPT-5.4 Nano (2026-03-17) (xHigh): benchmark results
Provider: OpenAI. Released 2026-03-17. Access: API.
Unified ELO 1691 ± 23, rank #384 of 2131 rated models, from 37 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Horangi 4 - GLP - Mathematical Reasoning | 98 | Score (%) | 98.6 |
| Horangi 4 - HumanEval (100-problem subset) | 100 | Pass rate (%) | 96.2 |
| Horangi 4 - Ko-AIME 2025 | 100 | Accuracy (%) | 96.2 |
| Horangi 4 - KoBBQ | 97 | Accuracy (%) | 94.7 |
| Horangi 4 - HRM8K | 96 | Accuracy (%) | 93.8 |
| Horangi 4 - IFEval-Ko | 92.5 | Instruction-following accuracy (%) | 93.3 |
| Horangi 4 - BigCodeBench (100-task subset) | 56.57 | Pass rate (%) | 88.9 |
| Horangi 4 - Ko-HLE | 34.02 | Accuracy (%) | 85.6 |
| Horangi 4 - GLP - Specialized Knowledge | 54.01 | Score (%) | 81.7 |
| Horangi 4 - SWE-bench Verified (80-task subset) | 53.75 | Resolved (%) | 75.5 |
| Horangi 4 - GLP - Coding | 70.11 | Score (%) | 75 |
| Horangi 4 - Ko-ARC-AGI | 56.52 | Accuracy (%) | 72.1 |
Interactive version: theaggregate.ai/model?slug=gpt-5-4-nano-2026-03-17-xhigh · How It Works · Data refreshed daily, snapshot 2026-10-09.