Compare / head-to-head
Claude Opus 4.1vsClaude 3.5 Sonnet
Claude Opus 4.1 leads 3 of 3 shared benchmarks. Claude 3.5 Sonnet is 5x cheaper per token. Both offer a 200K-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
3 – 0
Claude Opus 4.1 leads
Cheaper per token
Claude 3.5 Sonnet
5x cheaper, input + output
Larger context
Tie
both 200K tokens
Provider uptime (30d)
100%
Anthropic
Claude Opus 4.1
Anthropic · released 2025-08-05
textvision
Claude 3.5 Sonnet
Anthropic · released 2024-10-22
textvision
Quality
Benchmark matrix
3 shared · 3 only Claude Opus 4.1 · 1 only Claude 3.5 Sonnet| Benchmark | Claude Opus 4.1 | Claude 3.5 Sonnet | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 3 | ||||
| SWE-bench Verified | 74.5% ↗ | 49% ↗ | +25.5 pt | Claude Opus 4.1 |
| GPQA Diamond | 77.3% ↗epoch | 55.3% ↗epoch | +22 pt | Claude Opus 4.1 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 68.9% ↗epoch | 8.5% ↗epoch | +60.4 pt | Claude Opus 4.1 |
| Only Claude Opus 4.1 reports · 3 | ||||
| FrontierMath Tier 4 v2 (Epoch AI run) | 2.4% ↗epoch | not reported | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 12.6% ↗epoch | not reported | — | — |
| SWE-bench Verified (Epoch AI run) | 73.3% ↗epoch | not reported | — | — |
| Only Claude 3.5 Sonnet reports · 1 | ||||
| AIME 2025 | not reported | 3.3% ↗matharena | — | — |
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 4.1 minus Claude 3.5 Sonnet 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 4.1 | Claude 3.5 Sonnet | Edge |
|---|---|---|---|
| Context window | 200K tokens | 200K tokens | Tie |
| Max output | 32K tokens | 8K tokens | Claude Opus 4.1 |
| Input price / 1M | $15 ↗ | $3 ↗ | Claude 3.5 Sonnet |
| Output price / 1M | $75 ↗ | $15 ↗ | Claude 3.5 Sonnet |
| Cached input / 1M | $1.5 ↗ | $0.3 ↗ | Claude 3.5 Sonnet |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $90 | $18 | Claude 3.5 Sonnet |
| Modalities | text · vision | text · vision | Tie |
| Released | 2025-08-05 | 2024-10-22 | — |
| Cited benchmark scores | 6 | 4 | — |
Reliability
Anthropic status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Claude Opus 4.1 vs …
Models sharing the most benchmarksMore matchups
Claude 3.5 Sonnet vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Claude Opus 4.1 and Claude 3.5 Sonnet on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.