OpenAI · stable
OpenAI's documented GPT-5.6 model for cost-sensitive, high-volume API workloads.
Specialist evidence
Source-native operational evidence for GPT-5.6 Luna. Exact configurations remain separate. Costs are comparable only within the same selected benchmark/evaluation, and these rows never enter Overall Score.
| Evaluation | Exact configuration | Performance | Cost / task | Tokens / task | Execution |
|---|---|---|---|---|---|
| Artificial Analysis Coding Agents · 1.4 · composite Artificial Analysis Coding Agents · checked 2026-08-29 | gpt-5-6-luna-high Codex - GPT-5.6 Luna (high) | 51.7 | $0.180 | 9641370 | 83.8 steps |
| Artificial Analysis Coding Agents · 1.4 · composite Artificial Analysis Coding Agents · checked 2026-08-29 | gpt-5-6-luna-low Codex - GPT-5.6 Luna (low) | 25.1 | $0.039 | 1435666 | 34.3 steps |
| Artificial Analysis Coding Agents · 1.4 · composite Artificial Analysis Coding Agents · checked 2026-08-29 | gpt-5-6-luna-max Codex - GPT-5.6 Luna (max) | 57.2 | $0.288 | 15963259 | 114.6 steps |
| Artificial Analysis Coding Agents · 1.4 · composite Artificial Analysis Coding Agents · checked 2026-08-29 | gpt-5-6-luna-max Codex - GPT-5.6 Luna (none) | 19.1 | $0.069 | 3549957 | 54.3 steps |
| Artificial Analysis Coding Agents · 1.4 · composite Artificial Analysis Coding Agents · checked 2026-08-29 | gpt-5-6-luna-medium Codex - GPT-5.6 Luna (medium) | 42.0 | $0.088 | 4287328 | 57.1 steps |
| Artificial Analysis Coding Agents · 1.4 · composite Artificial Analysis Coding Agents · checked 2026-08-29 | gpt-5-6-luna-xhigh Codex - GPT-5.6 Luna (xhigh) | 53.0 | $0.236 | 12806609 | 96.2 steps |
| CursorBench · 3.2 · main CursorBench · checked 2026-08-29 | gpt-5-6-luna-high GPT-5.6 Luna High | 56.8% | $0.160 | 15141 | 40 steps |
| CursorBench · 3.2 · main CursorBench · checked 2026-08-29 | gpt-5-6-luna-low GPT-5.6 Luna Low | 37.6% | $0.030 | 3209 | 17 steps |
| CursorBench · 3.2 · main CursorBench · checked 2026-08-29 | gpt-5-6-luna-max GPT-5.6 Luna Max | 61.1% | $0.390 | 87973 | 61 steps |
| CursorBench · 3.2 · main CursorBench · checked 2026-08-29 | gpt-5-6-luna-medium GPT-5.6 Luna Medium | 47.7% | $0.080 | 7095 | 28 steps |
| CursorBench · 3.2 · main CursorBench · checked 2026-08-29 | gpt-5-6-luna-xhigh GPT-5.6 Luna Extra High | 57.7% | $0.230 | 22480 | 48 steps |
| Terminal-Bench 2.1 · 2.1 · verified Terminal-Bench 2.1 · checked 2026-08-29 | gpt-5-6-luna-max Codex; reasoning max; Terminal-Bench 2.1 verified submission. | 75.7% | $2.71 | — | — |
