Compare / head-to-head
Claude Opus 4vsGPT-5 mini
Claude Opus 4 and GPT-5 mini split their 4 shared benchmarks evenly. GPT-5 mini is 40x cheaper per token. GPT-5 mini has the larger context window (400K tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
2 – 2
even split
Cheaper per token
GPT-5 mini
40x cheaper, input + output
Larger context
GPT-5 mini
400K tokens
Provider uptime (30d)
100% · 95.4802%
Anthropic · OpenAI
Claude Opus 4
Anthropic · released 2025-05-22
textvision
GPT-5 mini
OpenAI · released 2025-08-07
textvision
Quality
Benchmark matrix
4 shared · 2 only Claude Opus 4 · 4 only GPT-5 mini| Benchmark | Claude Opus 4 | GPT-5 mini | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 4 | ||||
| SWE-bench Verified | 72.5% ↗ | 71% ↗ | +1.5 pt | Claude Opus 4 |
| GPQA Diamond | 76.3% ↗epoch | 81.6% ↗ | -5.3 pt | GPT-5 mini |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 64.4% ↗epoch | 86.7% ↗epoch | -22.3 pt | GPT-5 mini |
| SWE-bench Verified (Epoch AI run) | 70.7% ↗epoch | 64.7% ↗epoch | +6 pt | Claude Opus 4 |
| Only Claude Opus 4 reports · 2 | ||||
| AIME 2024 (no extended thinking) | 33.9% ↗ | not reported | — | — |
| Terminal-bench | 43.2% ↗ | not reported | — | — |
| Only GPT-5 mini reports · 4 | ||||
| AIME 2025 | not reported | 87.5% ↗matharena ⚠ | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | not reported | 12.2% ↗epoch | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | not reported | 46.7% ↗epoch | — | — |
| SimpleQA Verified | not reported | 21.6% ↗epoch | — | — |
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 GPT-5 mini 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 | GPT-5 mini | Edge |
|---|---|---|---|
| Context window | 200K tokens | 400K tokens | GPT-5 mini |
| Max output | 32K tokens | 128K tokens | GPT-5 mini |
| Input price / 1M | $15 ↗ | $0.25 ↗ | GPT-5 mini |
| Output price / 1M | $75 ↗ | $2 ↗ | GPT-5 mini |
| Cached input / 1M | $1.5 ↗ | $0.025 ↗ | GPT-5 mini |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $90 | $2.25 | GPT-5 mini |
| Modalities | text · vision | text · vision | Tie |
| Released | 2025-05-22 | 2025-08-07 | — |
| Cited benchmark scores | 6 | 9 | — |
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
GPT-5 mini 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 GPT-5 mini on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.