Compare / head-to-head
Gemma 4 31BvsGPT-5.6 Luna
GPT-5.6 Luna leads 1 of 1 shared benchmark. 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
0 – 1
GPT-5.6 Luna leads
Cheaper per token
—
list price, input + output
Larger context
GPT-5.6 Luna
1.1M tokens
Provider uptime (30d)
100% · 95.3216%
Google · OpenAI
Gemma 4 31B
Google · released 2026-04-02
textvision
- Context
- 256K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 6 · 5 core
GPT-5.6 Luna
OpenAI · released 2026-07-09
textvision
Quality
Benchmark matrix
1 shared · 5 only Gemma 4 31B · 6 only GPT-5.6 Luna| Benchmark | Gemma 4 31B | GPT-5.6 Luna | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 1 | ||||
| GPQA Diamond | 84.3% ↗ | 92.3% ↗ | -8 pt | GPT-5.6 Luna |
| Only Gemma 4 31B reports · 5 | ||||
| MMLU-Pro | 85.2% ↗ | not reported | — | — |
| AIME 2026 | 89.2% ↗ | not reported | — | — |
| Humanity's Last Exam (no tools) | 19.5% ↗ | not reported | — | — |
| LMArena Elo | 1441.7 ↗ | not reported | — | — |
| LiveCodeBench v6 | 80% ↗ | not reported | — | — |
| Only GPT-5.6 Luna reports · 6 | ||||
| DeepSWE v1.1 | not reported | 67.2% ↗ | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | not reported | 61% ↗epoch | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | not reported | 82.1% ↗epoch | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | not reported | 98.3% ↗epoch | — | — |
| SimpleQA Verified | not reported | 41% ↗epoch | — | — |
| 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 Gemma 4 31B 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 | Gemma 4 31B | GPT-5.6 Luna | Edge |
|---|---|---|---|
| Context window | 256K tokens | 1.1M tokens | GPT-5.6 Luna |
| Max output | — | 128K tokens | — |
| Input price / 1M | — | $0.2 ↗ | — |
| Output price / 1M | — | $1.2 ↗ | — |
| Cached input / 1M | — | $0.02 ↗ | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | $1.4 | — |
| Modalities | text · vision | text · vision | Tie |
| Released | 2026-04-02 | 2026-07-09 | — |
| Cited benchmark scores | 6 | 8 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Gemma 4 31B 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 Gemma 4 31B and GPT-5.6 Luna on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.