Compare / head-to-head
GPT-5.6 LunavsMinistral 3 14B
GPT-5.6 Luna leads 1 of 1 shared benchmark. Ministral 3 14B is 3.5x 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
1 – 0
GPT-5.6 Luna leads
Cheaper per token
Ministral 3 14B
3.5x cheaper, input + output
Larger context
GPT-5.6 Luna
1.1M tokens
Provider uptime (30d)
95.2096% · 100%
OpenAI · Mistral AI
GPT-5.6 Luna
OpenAI · released 2026-07-09
textvision
Ministral 3 14B
Mistral AI · released 2025-12-02
textvision
Quality
Benchmark matrix
1 shared · 6 only GPT-5.6 Luna · 2 only Ministral 3 14B| Benchmark | GPT-5.6 Luna | Ministral 3 14B | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 1 | ||||
| GPQA Diamond | 92.3% ↗ | 71.2% ↗ | +21.1 pt | GPT-5.6 Luna |
| Only GPT-5.6 Luna reports · 6 | ||||
| DeepSWE v1.1 | 67.2% ↗ | not reported | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | 61% ↗epoch | not reported | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 82.1% ↗epoch | not reported | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 98.3% ↗epoch | not reported | — | — |
| SimpleQA Verified | 41% ↗epoch | not reported | — | — |
| SWE-Bench Pro | 62.7% ↗ | not reported | — | — |
| Only Ministral 3 14B reports · 2 | ||||
| AIME 2025 | not reported | 85% ↗ | — | — |
| LiveCodeBench | not reported | 64.6% ↗ | — | — |
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 GPT-5.6 Luna minus Ministral 3 14B 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 | GPT-5.6 Luna | Ministral 3 14B | Edge |
|---|---|---|---|
| Context window | 1.1M tokens | 256K tokens | GPT-5.6 Luna |
| Max output | 128K tokens | — | — |
| Input price / 1M | $0.2 ↗ | $0.2 ↗ | Tie |
| Output price / 1M | $1.2 ↗ | $0.2 ↗ | Ministral 3 14B |
| Cached input / 1M | $0.02 ↗ | $0.02 ↗ | Tie |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $1.4 | $0.4 | Ministral 3 14B |
| Modalities | text · vision | text · vision | Tie |
| Released | 2026-07-09 | 2025-12-02 | — |
| Cited benchmark scores | 8 | 3 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
GPT-5.6 Luna vs …
Models sharing the most benchmarksMore matchups
Ministral 3 14B vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run GPT-5.6 Luna and Ministral 3 14B on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.