Compare / head-to-head
Claude Opus 4.6vsClaude Sonnet 4.5
Claude Opus 4.6 leads 16 of 16 shared benchmarks. Claude Sonnet 4.5 is 1.7x cheaper per token. Claude Opus 4.6 has the larger context window (1M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
16 – 0
Claude Opus 4.6 leads
Cheaper per token
Claude Sonnet 4.5
1.7x cheaper, input + output
Larger context
Claude Opus 4.6
1M tokens
Provider uptime (30d)
100%
Anthropic
Claude Opus 4.6
Anthropic · released 2026-02-05
textvision
Claude Sonnet 4.5
Anthropic · released 2025-09-29
textvision
Quality
Benchmark matrix
16 shared · 2 only Claude Opus 4.6 · 4 only Claude Sonnet 4.5| Benchmark | Claude Opus 4.6 | Claude Sonnet 4.5 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 16 | ||||
| SWE-bench Verified | 80.8% ↗ | 77.2% ↗ | +3.6 pt | Claude Opus 4.6 |
| GPQA Diamond | 91.3% ↗ | 83.4% ↗ | +7.9 pt | Claude Opus 4.6 |
| ARC-AGI-2 (Verified) | 68.8% ↗ | 13.6% ↗ | +55.2 pt | Claude Opus 4.6 |
| FrontierMath Tier 4 v2 (Epoch AI run) | 26.8% ↗epoch | 2.4% ↗epoch | +24.4 pt | Claude Opus 4.6 |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 66% ↗epoch | 23.9% ↗epoch | +42.1 pt | Claude Opus 4.6 |
| MCP Atlas | 59.5% ↗ | 43.8% ↗ | +15.7 pt | Claude Opus 4.6 |
| MMMLU | 91.1% ↗ | 89.5% ↗ | +1.6 pt | Claude Opus 4.6 |
| MMMU-Pro (no tools) | 73.9% ↗ | 63.4% ↗ | +10.5 pt | Claude Opus 4.6 |
| MMMU-Pro (with tools) | 77.3% ↗ | 68.9% ↗ | +8.4 pt | Claude Opus 4.6 |
| OSWorld-Verified | 72.7% ↗ | 61.4% ↗ | +11.3 pt | Claude Opus 4.6 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 94.4% ↗epoch | 77.8% ↗epoch | +16.6 pt | Claude Opus 4.6 |
| SimpleQA Verified | 47% ↗epoch | 30.7% ↗epoch | +16.3 pt | Claude Opus 4.6 |
| SWE-bench Verified (Epoch AI run) | 78.7% ↗epoch | 71.3% ↗epoch | +7.4 pt | Claude Opus 4.6 |
| Tau2-bench Retail | 91.9% ↗ | 86.2% ↗ | +5.7 pt | Claude Opus 4.6 |
| Tau2-bench Telecom | 99.3% ↗ | 98% ↗ | +1.3 pt | Claude Opus 4.6 |
| Terminal-Bench 2.0 | 65.4% ↗ | 51% ↗ | +14.4 pt | Claude Opus 4.6 |
| Only Claude Opus 4.6 reports · 2 | ||||
| AIME 2026 | 96.7% ↗matharena | not reported | — | — |
| LMArena Elo | 1497.5 ↗ | not reported | — | — |
| Only Claude Sonnet 4.5 reports · 4 | ||||
| AIME 2025 | not reported | 84.2% ↗matharena ⚠ | — | — |
| Humanity's Last Exam (no tools) | not reported | 17.7% ↗ | — | — |
| GDPval-AA | not reported | 1276 ↗ | — | — |
| Humanity's Last Exam (with tools) | not reported | 33.6% ↗ | — | — |
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 Claude Opus 4.6 minus Claude Sonnet 4.5 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 4.6 | Claude Sonnet 4.5 | Edge |
|---|---|---|---|
| Context window | 1M tokens | 200K tokens | Claude Opus 4.6 |
| Max output | 128K tokens | 64K tokens | Claude Opus 4.6 |
| Input price / 1M | $5 ↗ | $3 ↗ | Claude Sonnet 4.5 |
| Output price / 1M | $25 ↗ | $15 ↗ | Claude Sonnet 4.5 |
| Cached input / 1M | $0.5 ↗ | $0.3 ↗ | Claude Sonnet 4.5 |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $30 | $18 | Claude Sonnet 4.5 |
| Modalities | text · vision | text · vision | Tie |
| Released | 2026-02-05 | 2025-09-29 | — |
| Cited benchmark scores | 19 | 21 | — |
Reliability
Anthropic status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Claude Opus 4.6 vs …
Models sharing the most benchmarksMore matchups
Claude Sonnet 4.5 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Claude Opus 4.6 and Claude Sonnet 4.5 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.