Compare / head-to-head
Claude Opus 4vsMinistral 3 3B
Claude Opus 4 leads 1 of 1 shared benchmark. Ministral 3 3B is 450x cheaper per token. 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
1 – 0
Claude Opus 4 leads
Cheaper per token
Ministral 3 3B
450x cheaper, input + output
Larger context
Ministral 3 3B
256K tokens
Provider uptime (30d)
100% · 100%
Anthropic · Mistral AI
Claude Opus 4
Anthropic · released 2025-05-22
textvision
Ministral 3 3B
Mistral AI · released 2025-12-02
textvision
Quality
Benchmark matrix
1 shared · 5 only Claude Opus 4 · 2 only Ministral 3 3B| Benchmark | Claude Opus 4 | Ministral 3 3B | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 1 | ||||
| GPQA Diamond | 76.3% ↗epoch | 53.4% ↗ | +22.9 pt | Claude Opus 4 |
| Only Claude Opus 4 reports · 5 | ||||
| SWE-bench Verified | 72.5% ↗ | not reported | — | — |
| AIME 2024 (no extended thinking) | 33.9% ↗ | not reported | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 64.4% ↗epoch | not reported | — | — |
| SWE-bench Verified (Epoch AI run) | 70.7% ↗epoch | not reported | — | — |
| Terminal-bench | 43.2% ↗ | not reported | — | — |
| Only Ministral 3 3B reports · 2 | ||||
| AIME 2025 | not reported | 72.1% ↗ | — | — |
| 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 Claude Opus 4 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 | Claude Opus 4 | Ministral 3 3B | Edge |
|---|---|---|---|
| Context window | 200K tokens | 256K tokens | Ministral 3 3B |
| Max output | 32K tokens | — | — |
| Input price / 1M | $15 ↗ | $0.1 ↗ | Ministral 3 3B |
| Output price / 1M | $75 ↗ | $0.1 ↗ | Ministral 3 3B |
| Cached input / 1M | $1.5 ↗ | $0.01 ↗ | Ministral 3 3B |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $90 | $0.2 | Ministral 3 3B |
| Modalities | text · vision | text · vision | Tie |
| Released | 2025-05-22 | 2025-12-02 | — |
| Cited benchmark scores | 6 | 3 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Claude Opus 4 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 Claude Opus 4 and Ministral 3 3B on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.