Compare / head-to-head
Claude Opus 4.6vsClaude Opus 4.7
Claude Opus 4.7 leads 8 of 10 shared benchmarks. Both list the same combined token price. Both offer a 1M-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
2 – 8
Claude Opus 4.7 leads
Cheaper per token
Tie
list price, input + output
Larger context
Tie
both 1M tokens
Provider uptime (30d)
100%
Anthropic
Claude Opus 4.6
Anthropic · released 2026-02-05
textvision
Claude Opus 4.7
Anthropic · released 2026-04-16
textvision
Quality
Benchmark matrix
10 shared · 8 only Claude Opus 4.6 · 7 only Claude Opus 4.7| Benchmark | Claude Opus 4.6 | Claude Opus 4.7 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 10 | ||||
| SWE-bench Verified | 80.8% ↗ | 87.6% ↗ | -6.8 pt | Claude Opus 4.7 |
| GPQA Diamond | 91.3% ↗ | 94.2% ↗ | -2.9 pt | Claude Opus 4.7 |
| AIME 2026 | 96.7% ↗matharena | 95.8% ↗matharena ⚠ | +0.9 pt | Claude Opus 4.6 |
| LMArena Elo | 1497.5 ↗ | 1483.4 ↗ | +14.1 | Claude Opus 4.6 |
| FrontierMath Tier 4 v2 (Epoch AI run) | 26.8% ↗epoch | 31.7% ↗epoch | -4.9 pt | Claude Opus 4.7 |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 66% ↗epoch | 70.2% ↗epoch | -4.2 pt | Claude Opus 4.7 |
| OSWorld-Verified | 72.7% ↗ | 82.8% ↗ | -10.1 pt | Claude Opus 4.7 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 94.4% ↗epoch | 97.8% ↗epoch | -3.4 pt | Claude Opus 4.7 |
| SimpleQA Verified | 47% ↗epoch | 51.7% ↗epoch | -4.7 pt | Claude Opus 4.7 |
| SWE-bench Verified (Epoch AI run) | 78.7% ↗epoch | 83.5% ↗epoch | -4.8 pt | Claude Opus 4.7 |
| Only Claude Opus 4.6 reports · 8 | ||||
| ARC-AGI-2 (Verified) | 68.8% ↗ | not reported | — | — |
| MCP Atlas | 59.5% ↗ | not reported | — | — |
| MMMLU | 91.1% ↗ | not reported | — | — |
| MMMU-Pro (no tools) | 73.9% ↗ | not reported | — | — |
| MMMU-Pro (with tools) | 77.3% ↗ | not reported | — | — |
| Tau2-bench Retail | 91.9% ↗ | not reported | — | — |
| Tau2-bench Telecom | 99.3% ↗ | not reported | — | — |
| Terminal-Bench 2.0 | 65.4% ↗ | not reported | — | — |
| Only Claude Opus 4.7 reports · 7 | ||||
| Humanity's Last Exam (no tools) | not reported | 46.9% ↗ | — | — |
| BrowseComp | not reported | 79.8% ↗ | — | — |
| Humanity's Last Exam (with tools) | not reported | 54.7% ↗ | — | — |
| SWE-bench Multilingual | not reported | 80.5% ↗ | — | — |
| SWE-bench Multimodal | not reported | 34.5% ↗ | — | — |
| SWE-Bench Pro | not reported | 64.3% ↗ | — | — |
| Terminal-Bench 2.1 | not reported | 66.1% ↗ | — | — |
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 Opus 4.7 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 Opus 4.7 | Edge |
|---|---|---|---|
| Context window | 1M tokens | 1M tokens | Tie |
| Max output | 128K tokens | 128K tokens | Tie |
| Input price / 1M | $5 ↗ | $5 ↗ | Tie |
| Output price / 1M | $25 ↗ | $25 ↗ | Tie |
| Cached input / 1M | $0.5 ↗ | $0.5 ↗ | Tie |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $30 | $30 | Tie |
| Modalities | text · vision | text · vision | Tie |
| Released | 2026-02-05 | 2026-04-16 | — |
| Cited benchmark scores | 19 | 18 | — |
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 Opus 4.7 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 Opus 4.7 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.