Compare / head-to-head
Gemini 3.8 FlashvsGPT-5.6 Luna
Gemini 3.8 Flash leads 4 of 6 shared benchmarks. GPT-5.6 Luna is 3.2x cheaper per token. GPT-5.6 Luna has the larger context window (1.1M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
4 – 2
Gemini 3.8 Flash leads
Cheaper per token
GPT-5.6 Luna
3.2x cheaper, input + output
Larger context
GPT-5.6 Luna
1.1M tokens
Provider uptime (30d)
100% · 94.8387%
Google · OpenAI
Gemini 3.8 Flash
Google · released 2026-09-02
textvisionaudio
GPT-5.6 Luna
OpenAI · released 2026-07-09
textvision
Quality
Benchmark matrix
6 shared · 9 only Gemini 3.8 Flash · 1 only GPT-5.6 Luna| Benchmark | Gemini 3.8 Flash | GPT-5.6 Luna | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 6 | ||||
| GPQA Diamond | 95.3% ↗ | 92.3% ↗ | +3 pt | Gemini 3.8 Flash |
| DeepSWE v1.1 | 73.7% ↗ | 67.2% ↗ | +6.5 pt | Gemini 3.8 Flash |
| FrontierMath Tier 4 v2 (Epoch AI run) | 22% ↗epoch | 61% ↗epoch | -39 pt | GPT-5.6 Luna |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 68.4% ↗epoch | 82.1% ↗epoch | -13.7 pt | GPT-5.6 Luna |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 98.9% ↗epoch | 98.3% ↗epoch | +0.6 pt | Gemini 3.8 Flash |
| SimpleQA Verified | 69.7% ↗epoch | 41% ↗epoch | +28.7 pt | Gemini 3.8 Flash |
| Only Gemini 3.8 Flash reports · 9 | ||||
| CharXiv Reasoning (no tools) | 86.2% ↗ | not reported | — | — |
| GDPVal-AA v2 | 1545 ↗ | not reported | — | — |
| Harvey's Legal Agent Benchmark | 10% ↗ | not reported | — | — |
| HLE-Verified | 54.9% ↗ | not reported | — | — |
| LABBench2 | 86.2% ↗ | not reported | — | — |
| OSWorld-2.0 | 59% ↗ | not reported | — | — |
| Terminal-bench 2.1 | 89.4% ↗ | not reported | — | — |
| Terminal-bench 4.0 | 19.1% ↗ | not reported | — | — |
| Vals Finance Agent v2 | 61.4% ↗ | not reported | — | — |
| Only GPT-5.6 Luna reports · 1 | ||||
| SWE-Bench Pro | not reported | 62.7% ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Gemini 3.8 Flash minus GPT-5.6 Luna in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | Gemini 3.8 Flash | GPT-5.6 Luna | Edge |
|---|---|---|---|
| Context window | 1.0M tokens | 1.1M tokens | GPT-5.6 Luna |
| Max output | 66K tokens | 128K tokens | GPT-5.6 Luna |
| Input price / 1M | $0.75 ↗ | $0.2 ↗ | GPT-5.6 Luna |
| Output price / 1M | $3.75 ↗ | $1.2 ↗ | GPT-5.6 Luna |
| Cached input / 1M | $0.075 ↗ | $0.02 ↗ | GPT-5.6 Luna |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $4.5 | $1.4 | GPT-5.6 Luna |
| Modalities | text · vision · audio | text · vision | Gemini 3.8 Flash |
| Released | 2026-09-02 | 2026-07-09 | — |
| Cited benchmark scores | 16 | 8 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Gemini 3.8 Flash vs …
Models sharing the most benchmarksMore matchups
GPT-5.6 Luna vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Gemini 3.8 Flash and GPT-5.6 Luna on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.