Claude Sonnet 5vsClaude Sonnet 4.6
Across 7 shared benchmarks, Claude Sonnet 5 leads overall: Claude Sonnet 5 wins 6, Claude Sonnet 4.6 wins 1, with 0 ties and an average score difference of +5.78.
Claude Sonnet 5
Anthropic · 2026-06-30 · Multimodal model
Claude Sonnet 4.6
Anthropic · 2026-02-17 · Chat model
Claude Sonnet 56 wins(86%)(14%)1 winClaude Sonnet 4.6
Benchmark scores
Grouped by capability, sorted by largest gap within each. 7 shared benchmarks.
Coding and Software Engineer
Claude Sonnet 5 2/2| Benchmark | Claude Sonnet 5 | Claude Sonnet 4.6 | Diff |
|---|---|---|---|
| DeepSWE | 5417 / 28Deep Thinking (With Tools) | 3026 / 28Thinking High (With Tools) | +24 |
| SWE-bench Verified | 85.207 / 114极高强度思考（工具） | 79.6018 / 114Thinking (No Tools) | +5.60 |
AI Agent - Information Search
Claude Sonnet 5 1/1| Benchmark | Claude Sonnet 5 | Claude Sonnet 4.6 | Diff |
|---|---|---|---|
| BrowseComp | 84.707 / 54Thinking (With Tools + Internet) | 74.7027 / 54Thinking (With Tools) | +10 |
AI Agent - Tool Usage
Claude Sonnet 5 1/1| Benchmark | Claude Sonnet 5 | Claude Sonnet 4.6 | Diff |
|---|---|---|---|
| OSWorld-Verified | 81.206 / 26极高强度思考（工具） | 72.5017 / 26Thinking (With Tools) | +8.70 |
General Evaluation
Claude Sonnet 5 1/1| Benchmark | Claude Sonnet 5 | Claude Sonnet 4.6 | Diff |
|---|---|---|---|
| GPQA Diamond | 90.5333 / 224极高强度思考（无工具） | 89.9042 / 224Thinking (No Tools) | +0.63 |
General Knowledge
Claude Sonnet 5 1/1| Benchmark | Claude Sonnet 5 | Claude Sonnet 4.6 | Diff |
|---|---|---|---|
| HLE | 57.409 / 181极高强度思考（工具） | 4934 / 181Thinking (With Tools) | +8.40 |
Writing and Creative Capabilities
Claude Sonnet 4.6 1/1| Benchmark | Claude Sonnet 5 | Claude Sonnet 4.6 | Diff |
|---|---|---|---|
| Creative Writing | 1,78818 / 99Normal (No Tools) | 1,80515 / 99Normal (No Tools) | -16.90 |
Specs
| Field | Claude Sonnet 5 | Claude Sonnet 4.6 |
|---|---|---|
| Publisher | Anthropic | Anthropic |
| Release date | 2026-06-30 | 2026-02-17 |
| Model type | Multimodal model | Chat model |
| Architecture | Dense | Dense |
| Parameters | Not available | Not available |
| Context length | 1M | 1M |
| Max output | 128K | 8K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | Claude Sonnet 5 | Claude Sonnet 4.6 |
|---|---|---|
| Text input | $2 / 1M tokens | $3 / 1M tokens |
| Text output | $10 / 1M tokens | $15 / 1M tokens |
| Cache read | $0.3 / 1M tokens | $0.3 / 1M tokens |
| Cache write | $3.75 / 1M tokens | $3.75 / 1M tokens |
Summary
- Claude Sonnet 5leads in:Coding and Software Engineer (2/2), AI Agent - Information Search (1/1), AI Agent - Tool Usage (1/1), General Evaluation (1/1), General Knowledge (1/1)
- Claude Sonnet 4.6leads in:Writing and Creative Capabilities (1/1)
On average across the 7 shared benchmarks, Claude Sonnet 5 scores 5.78 higher.
Largest single-benchmark gap: DeepSWE — Claude Sonnet 5 54 vs Claude Sonnet 4.6 30 (+24).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.