Claude Sonnet 4.6vsClaude Opus 4.6
Across 13 shared benchmarks, Claude Opus 4.6 leads overall: Claude Sonnet 4.6 wins 1, Claude Opus 4.6 wins 12, with 0 ties and an average score difference of -123.30.
Claude Sonnet 4.6
Anthropic · 2026-02-17 · Chat model
Claude Opus 4.6
Anthropic · 2026-02-05 · Reasoning model
Claude Sonnet 4.61 win(8%)(92%)12 winsClaude Opus 4.6
Benchmark scores
Grouped by capability, sorted by largest gap within each. 13 shared benchmarks.
General Knowledge
Claude Opus 4.6 4/4| Benchmark | Claude Sonnet 4.6 | Claude Opus 4.6 | Diff |
|---|---|---|---|
| ARC-AGI-2 | 58.3021 / 62 | 66.3017 / 62Extended (no tools) | -8 |
| HLE | 4932 / 172 | 5318 / 172Extended (with tools, internet) | -4 |
| GPQA Diamond | 89.9024 / 187 | 91.3115 / 187Extended (no tools) | -1.41 |
| LiveBench | 75.4712 / 115Thinking Medium (No Tools) | 76.338 / 115Thinking High (No Tools) | -0.86 |
AI Agent - Tool Usage
Claude Opus 4.6 3/3| Benchmark | Claude Sonnet 4.6 | Claude Opus 4.6 | Diff |
|---|---|---|---|
| MCP-Atlas | 69.5017 / 27Normal (With Tools) | 76.8010 / 27Deep Thinking (With Tools) | -7.30 |
| Terminal Bench 2.0 | 59.1022 / 47 | 65.4011 / 47Extended (with tools) | -6.30 |
| OSWorld-Verified | 72.5016 / 24 | 72.7015 / 24Extended (with tools) | -0.20 |
Agent Level Benchmark
Claude Opus 4.6 1/1| Benchmark | Claude Sonnet 4.6 | Claude Opus 4.6 | Diff |
|---|---|---|---|
| τ²-Bench - Telecom | 97.909 / 35 | 99.252 / 35Extended (with tools) | -1.35 |
AI Agent - Information Search
Claude Opus 4.6 1/1| Benchmark | Claude Sonnet 4.6 | Claude Opus 4.6 | Diff |
|---|---|---|---|
| BrowseComp | 74.7027 / 53 | 8411 / 53Thinking (With Tools + Internet) | -9.30 |
Claw-style Agent Evaluation
Claude Sonnet 4.6 1/1| Benchmark | Claude Sonnet 4.6 | Claude Opus 4.6 | Diff |
|---|---|---|---|
| Pinch Bench | 885 / 37Thinking (With Tools) | 87.407 / 37Thinking (With Tools) | +0.60 |
Coding and Software Engineer
Claude Opus 4.6 1/1| Benchmark | Claude Sonnet 4.6 | Claude Opus 4.6 | Diff |
|---|---|---|---|
| SWE-bench Verified | 79.6018 / 112 | 80.8410 / 112Extended (with tools) | -1.24 |
Math and Reasoning
Claude Opus 4.6 1/1| 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 |
Productivity Knowledge
Claude Opus 4.6 1/1| Benchmark | Claude Sonnet 4.6 | Claude Opus 4.6 | Diff |
|---|---|---|---|
| GDPval-AA | 5711 / 21 | 1,6063 / 21Extended (with tools, internet) | -1,549 |
Specs
| Field | Claude Sonnet 4.6 | Claude Opus 4.6 |
|---|---|---|
| Publisher | Anthropic | Anthropic |
| Release date | 2026-02-17 | 2026-02-05 |
| Model type | Chat model | Reasoning model |
| Architecture | Dense | Dense |
| Parameters | Not available | Not available |
| Context length | 1M | 1000K |
| Max output | 8K | 64K |
API pricing
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 |
Summary
- Claude Sonnet 4.6leads in:Claw-style Agent Evaluation (1/1)
- Claude Opus 4.6leads in:General Knowledge (4/4), AI Agent - Tool Usage (3/3), Agent Level Benchmark (1/1), AI Agent - Information Search (1/1), Coding and Software Engineer (1/1), Math and Reasoning (1/1), Productivity Knowledge (1/1)
On average across the 13 shared benchmarks, Claude Opus 4.6 scores 123.30 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.