Gemini 3.8 Flash vs GPT-6 Luna.
Verdict by category, tale of the tape, shared benchmarks only, and cost at three workloads — all from the tracked data.
Verdict by category
| Category | Gemini 3.8 Flash | GPT-6 Luna | Winner |
|---|---|---|---|
| League Score | 57.8 | 55.1 | Gemini 3.8 Flash |
| Coding (SWE-bench %) | — | — | — |
| Reasoning (GPQA %) | 95.0 | — | — |
| Context (tokens) | 1048576 | 1050000 | GPT-6 Luna |
| Speed (tok/s) | — | — | — |
| Price (blended $/1M) | $1.50 | $0.20 | GPT-6 Luna (cheaper) |
Tale of the tape
| Spec | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Maker | Google DeepMind | OpenAI |
| Released | Sep 2, 2026 | Sep 22, 2026 |
| League Score | 58 | 55 |
| Context | 1,048,576 tokens | 1,050,000 tokens |
| Max output | 65,536 | 128,000 |
| $/1M input | $0.75 | $0.10 |
| $/1M output | $3.75 | $0.50 |
| Weights | Closed | Closed |
| Speed | — | — |
Head-to-head benchmarks (shared only)
| Benchmark | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| LiveBench overall | 59.2 | 64.6 |
Cost at three workloads
| Workload | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Light — 1M in / 250K out | $1.69 | $0.23 |
| Standard — 10M in / 2.5M out | $16.88 | $2.25 |
| Long-context — 50M in / 5M out | $56.25 | $7.50 |
The pick
Pick Gemini 3.8 Flash if you want the higher overall League Score.
Pick GPT-6 Luna if you need the bigger context window; you want the lower running cost.
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, Gemini 3.8 Flash or GPT-6 Luna?
Gemini 3.8 Flash leads on overall League Score, 58 to 55 — a gap of 3 points on a composite of sourced benchmarks. That is overall form, not every category: check the per-category verdicts before choosing.
Which is cheaper, Gemini 3.8 Flash or GPT-6 Luna?
GPT-6 Luna is cheaper: $0.20 vs $1.50 blended per 1M tokens (3:1 input/output mix) — about 7.5x less per token.
Which has the bigger context window, Gemini 3.8 Flash or GPT-6 Luna?
GPT-6 Luna, with 1.1M of context against 1M for Gemini 3.8 Flash.
Are Gemini 3.8 Flash and GPT-6 Luna open source?
Gemini 3.8 Flash is closed weights — API access only; GPT-6 Luna is closed weights — API access only.