GPT-5.6 Luna: benchmark results
OpenAI's fast, low-cost GPT-5.6 tier. Provider: OpenAI. Released 2026-07-09. Access: API.
Unified ELO 1690 ± 1, rank #67 of 1392 rated models, from 210 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AgentBattler | 56.21 | Pooled Score (%) | 100 |
| Coarena - Task Completion | 89.1 | Completion Rate (%) | 100 |
| YapBench | 27.8 | YapIndex (lower is better) | 98.1 |
| Vals AI CyberBench | 83.9 | Accuracy (%) | 95.7 |
| Creative Writing v3 | 1932.2 | Elo score (self-reported) | 95.5 |
| Clerk LLM Leaderboard | 83.6 | Avg score (%) | 95.2 |
| BenchmarkList ECI | 146.95 | Capability Index (ECI) | 94 |
| AIIQ Composite IQ | 129 | Composite IQ (self-reported) | 93.5 |
| Vellum - HumanEval | 93 | Pass@1 (%) | 93.5 |
| ZeroEval GPQA Diamond | 92.3 | GPQA Diamond Score | 93.5 |
| Nejumi 4 - GLP - Syntactic Analysis | 87.83 | Score (%) | 92.2 |
| LLM Stats Score | 45.38 | LLM Stats Score (conservative rating) | 92 |
Interactive version: theaggregate.ai/model?slug=gpt-5-6-luna · How It Works · Data refreshed daily, snapshot 2026-09-05.