Across 11 shared benchmarks, Claude Opus 4.6 leads overall: Claude Sonnet 4.6 wins 1, Claude Opus 4.6 wins 10, with 0 ties and an average score difference of -144.98.
Anthropic · 2026-02-17 · AI model
Anthropic · 2026-02-05 · Reasoning model
Grouped by capability, sorted by largest gap within each. 11 shared benchmarks.
| Benchmark | Claude Sonnet 4.6 | Claude Opus 4.6 | Diff |
|---|---|---|---|
| ARC-AGI-2 | 58.3017 / 58thinking | 66.3014 / 58Extended (no tools) | -8 |
| HLE | 4920 / 149thinking + 使用工具 | 538 / 149Extended (with tools, internet) | -4 |
| GPQA Diamond | 89.9018 / 175thinking | 91.3112 / 175Extended (no tools) | -1.41 |
| Benchmark | Claude Sonnet 4.6 | Claude Opus 4.6 | Diff |
|---|---|---|---|
| Terminal Bench 2.0 | 59.1019 / 43thinking + 使用工具 | 65.409 / 43Extended (with tools) | -6.30 |
| OSWorld-Verified | 72.507 / 14thinking + 使用工具 | 72.706 / 14Extended (with tools) | -0.20 |
| Benchmark | Claude Sonnet 4.6 | Claude Opus 4.6 | Diff |
|---|---|---|---|
| τ²-Bench - Telecom | 97.909 / 35thinking + 使用工具 | 99.252 / 35Extended (with tools) | -1.35 |
| Benchmark | Claude Sonnet 4.6 | Claude Opus 4.6 | Diff |
|---|---|---|---|
| BrowseComp | 74.7018 / 43thinking + 使用工具 | 846 / 43Thinking (With Tools + Internet) | -9.30 |
| Benchmark | Claude Sonnet 4.6 | Claude Opus 4.6 | Diff |
|---|---|---|---|
| Pinch Bench | 885 / 37Thinking (With Tools) | 87.407 / 37Thinking (With Tools) | +0.60 |
| Benchmark | Claude Sonnet 4.6 | Claude Opus 4.6 | Diff |
|---|---|---|---|
| SWE-bench Verified | 79.6013 / 103thinking | 80.846 / 103Extended (with tools) | -1.24 |
| Benchmark | Claude Sonnet 4.6 | Claude Opus 4.6 | Diff |
|---|---|---|---|
| FrontierMath - Tier 4 | 8.3034 / 80Thinking (No Tools, 16K Budget) | 22.9012 / 80最高（无工具） | -14.60 |
| Benchmark | Claude Sonnet 4.6 | Claude Opus 4.6 | Diff |
|---|---|---|---|
| GDPval-AA | 5710 / 20thinking | 1,6061 / 20Extended (with tools, internet) | -1,549 |
| Field | Claude Sonnet 4.6 | Claude Opus 4.6 |
|---|---|---|
| Publisher | Anthropic | Anthropic |
| Release date | 2026-02-17 | 2026-02-05 |
| Model type | AI model | Reasoning model |
| Architecture | Dense | Dense |
| Parameters | 0.0 | 0.0 |
| Context length | 1M | 1000K |
| Max output | 8192 | 65536 |
Prices use DataLearner records when available; missing fields are not inferred.
| Item | Claude Sonnet 4.6 | Claude Opus 4.6 |
|---|---|---|
| Text input | $3 / 1M tokens | $0.5 / 1M tokens |
| Text output | $15 / 1M tokens | $25 / 1M tokens |
| Cache read | $0.3 / 1M tokens | $0.5 / 1M tokens |
| Cache write | $3.75 / 1M tokens | $10 / 1M tokens |
On average across the 11 shared benchmarks, Claude Opus 4.6 scores 144.98 higher.
Largest single-benchmark gap: GDPval-AA — Claude Sonnet 4.6 57 vs Claude Opus 4.6 1,606 (-1,549).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.
