GPT-6 Luna vs MAI-Thinking-1.
Verdict by category, tale of the tape, shared benchmarks only, and cost at three workloads — all from the tracked data.
Verdict by category
| Category | GPT-6 Luna | MAI-Thinking-1 | Winner |
|---|---|---|---|
| League Score | 53.3 | 48.7 | GPT-6 Luna |
| Coding (SWE-bench %) | — | — | — |
| Reasoning (GPQA %) | — | 84.2 | — |
| Context (tokens) | 1050000 | 1000000 | GPT-6 Luna |
| Speed (tok/s) | — | — | — |
Tale of the tape
| Spec | GPT-6 Luna | MAI-Thinking-1 |
|---|---|---|
| Maker | OpenAI | Microsoft AI |
| Released | Sep 22, 2026 | Jun 2, 2026 |
| League Score | 53 | 49 |
| Context | 1,050,000 tokens | 1,000,000 tokens |
| Max output | 128,000 | — |
| $/1M input | $0.10 | — |
| $/1M output | $0.50 | — |
| Weights | Closed | Closed |
| Speed | — | — |
Head-to-head benchmarks (shared only)
| Benchmark | GPT-6 Luna | MAI-Thinking-1 |
|---|---|---|
| No shared benchmark measurements yet — shown as not measured, never interpolated. | ||
Cost at three workloads
| Workload | GPT-6 Luna | MAI-Thinking-1 |
|---|---|---|
| Light — 1M in / 250K out | $0.23 | — |
| Standard — 10M in / 2.5M out | $2.25 | — |
| Long-context — 50M in / 5M out | $7.50 | — |
The pick
Pick GPT-6 Luna if you want the higher overall League Score; you need the bigger context window.
All figures from the model database — sources and dates on each model page. Cost your own workload or compare a different pair.
Frequently asked questions
Which is better overall, GPT-6 Luna or MAI-Thinking-1?
GPT-6 Luna leads on overall League Score, 53 to 49 — a gap of 5 points on a composite of sourced benchmarks. That is overall form, not every category: check the per-category verdicts before choosing.
Which is cheaper, GPT-6 Luna or MAI-Thinking-1?
Only GPT-6 Luna has published API pricing in our database ($0.20 blended per 1M tokens); MAI-Thinking-1 has no tracked API price, so a like-for-like cost verdict is not possible.
Which has the bigger context window, GPT-6 Luna or MAI-Thinking-1?
GPT-6 Luna, with 1.1M of context against 1M for MAI-Thinking-1.
Are GPT-6 Luna and MAI-Thinking-1 open source?
GPT-6 Luna is closed weights — API access only; MAI-Thinking-1 is closed weights — API access only.