Models / GPT-6 Luna
GPT-6 Luna
OpenAI · Closed weights · Released Sep 22, 2026 · Price not listed
37Overall · rank 30
Score by job
~ is an early read: this model has results on too few benchmarks in that job to be ranked yet.
Compare GPT-6 Luna with
Badge for your README
Shows this model’s current rank. It updates with every data update.
Badge job
Overall
Coding
Agents
Reasoning
Math
Writing
Design
Coding
Early read ~30 · not ranked · 2 of 5 benchmarks
| Benchmark | Result | Variant | z |
|---|---|---|---|
| FrontierCode | 42.4% | gpt-6-luna_max | 0.10 |
| LMArena Coding | 1439 rating | gpt-6-luna-max | -1.98 |
Agents
Early read ~20 · not ranked · 1 of 4 benchmarks
| Benchmark | Result | Variant | z |
|---|---|---|---|
| APEX-Agents | 44.3% | gpt-6-luna_max | -0.73 |
Reasoning
38 · rank 31 · 2 of 4 benchmarks
| Benchmark | Result | Variant | z |
|---|---|---|---|
| GPQA Diamond | 90.5% | gpt-6-luna_max | -0.52 |
| ARC-AGI-2 | 59.3% | gpt-6-luna_max | -0.34 |
Math
51 · rank 23 · 5 of 5 benchmarks
| Benchmark | Result | Variant | z |
|---|---|---|---|
| FrontierMath Tiers 1–3 | 78.9% | gpt-6-luna_max | 0.62 |
| FrontierMath Tier 4 | 56.1% | gpt-6-luna_max | 0.43 |
| OTIS Mock AIME | 98.9% | gpt-6-luna_max | 0.68 |
| ProofBench | 64.0% | gpt-6-luna_unknown | 0.43 |
| LMArena Math | 1416 rating | gpt-6-luna-max | -2.07 |
Writing
12 · rank 47 · 2 of 2 benchmarks
| Benchmark | Result | Variant | z |
|---|---|---|---|
| LMArena Creative Writing | 1363 rating | gpt-6-luna-max | -2.25 |
| LMArena Instruction Following | 1409 rating | gpt-6-luna-max | -1.80 |
Design
47 · rank 22 · 1 of 1 benchmarks
| Benchmark | Result | Variant | z |
|---|---|---|---|
| LMArena WebDev | 1581 rating | gpt-6-luna-max | 0.12 |