Compare / head-to-head
gpt-oss-20bvsMinistral 3 3B
gpt-oss-20b leads 2 of 2 shared benchmarks. Ministral 3 3B has the larger context window (256K tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
2 – 0
gpt-oss-20b leads
Cheaper per token
—
list price, input + output
Larger context
Ministral 3 3B
256K tokens
Provider uptime (30d)
94.4444% · 100%
OpenAI · Mistral AI
gpt-oss-20b
OpenAI · released 2025-08-05
text
- Context
- 131K
- Max out
- 131K
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 6 · 5 core
Ministral 3 3B
Mistral AI · released 2025-12-02
textvision
Quality
Benchmark matrix
2 shared · 3 only gpt-oss-20b · 1 only Ministral 3 3B| Benchmark | gpt-oss-20b | Ministral 3 3B | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 2 | ||||
| GPQA Diamond | 71.5% ↗ | 53.4% ↗ | +18.1 pt | gpt-oss-20b |
| AIME 2025 | 89.2% ↗matharena ⚠ | 72.1% ↗ | +17.1 pt | gpt-oss-20b |
| Only gpt-oss-20b reports · 3 | ||||
| SWE-bench Verified | 60.7% ↗ | not reported | — | — |
| LMArena Elo | 1287.3 ↗ | not reported | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 65.3% ↗epoch | not reported | — | — |
| Only Ministral 3 3B reports · 1 | ||||
| LiveCodeBench | not reported | 54.8% ↗ | — | — |
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-oss-20b minus Ministral 3 3B 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-oss-20b | Ministral 3 3B | Edge |
|---|---|---|---|
| Context window | 131K tokens | 256K tokens | Ministral 3 3B |
| Max output | 131K tokens | — | — |
| Input price / 1M | — | $0.1 ↗ | — |
| Output price / 1M | — | $0.1 ↗ | — |
| Cached input / 1M | — | $0.01 ↗ | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | $0.2 | — |
| Modalities | text | text · vision | Ministral 3 3B |
| Released | 2025-08-05 | 2025-12-02 | — |
| Cited benchmark scores | 6 | 3 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
gpt-oss-20b vs …
Models sharing the most benchmarksMore matchups
Ministral 3 3B vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run gpt-oss-20b and Ministral 3 3B on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.