Claude Sonnet 5.5 Benchmark Details
Claude Sonnet 5.5 currently shows benchmark results led by Terminal-Bench 4.0 (1 / 104, score 70.60), Vibe Code Bench v1.1 (1 / 66, score 92.39), HLE (4 / 239, score 64.50). This page also compares it with 3 competitor models and 3 predecessor or same-series models, including performance and pricing views when available.
Benchmark Results
Benchmark Results
Knowledge Exams
4 evaluationsRepository Engineering
7 evaluationsCross-capability Suites
2 evaluationsOffice & Business
3 evaluationsLegal
2 evaluationsMathematics
2 evaluationsDocuments & Charts
2 evaluationsAgentic Development
2 evaluationsScientific Computing
1 evaluationsCode Generation & Editing
3 evaluationsMedical Reasoning
1 evaluationsCompetitor Comparison
Benchmark scores for Claude Sonnet 5.5 compared against top models in its class
12 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | Claude Sonnet 5.5Current | GPT-6 Sol | Muse Spark 1.3 | DeepSeek-V4.1-Flash |
|---|---|---|---|---|
64.50Thinking Level · High ｜ Tools | -- | -- | 63.90Thinking Level · High ｜ Tools | |
66.40Thinking Level · High ｜ Tools | 45.00Thinking Level · High ｜ Tools | 39.10Thinking Level · High ｜ Tools | 51.90Thinking Level · High ｜ Tools | |
71.00Thinking Level · High ｜ Tools | 68.80Thinking Level · High ｜ Tools | 75.40Thinking Level · High ｜ Tools | 74.20Thinking Level · High ｜ Tools | |
61.89Thinking Level · High ｜ Tools | -- | 25.80Thinking Level · High ｜ Tools | -- | |
77.75Thinking Level · Extra High | 79.25Thinking Level · High | 81.59Thinking Level · Extra High | 81.11Thinking Level · High | |
44.70Thinking Level · High ｜ Tools | 33.20Thinking Level · Extra High ｜ Tools | 49.40Thinking Level · High ｜ Tools | 54.80Thinking Level · High ｜ Tools | |
2.92Thinking Level · High ｜ Tools | 1.67Thinking Level · High ｜ Tools | 23.75Thinking Level · High ｜ Tools | 6.67Thinking Level · High ｜ Tools | |
48.08Thinking Level · High ｜ Tools | 28.85Thinking Level · High ｜ Tools | 55.29Thinking Level · High ｜ Tools | 41.35Thinking Level · High ｜ Tools | |
80.49Thinking Level · High ｜ Tools | 90.00Thinking Level · High ｜ Tools | 46.34Thinking Level · High ｜ Tools | -- | |
88.77Thinking Level · High ｜ Tools | 89.82Thinking Level · High ｜ Tools | 74.39Thinking Level · Extra High ｜ Tools | -- | |
81.11Thinking Level · High ｜ Tools | 74.81Thinking Level · High ｜ Tools | -- | 67.78Thinking Level · High ｜ Tools | |
90.20Thinking Level · High ｜ Tools | -- | -- | 78.90Thinking Level · High ｜ Tools |
Standard API Pricing: Claude Sonnet 5.5 vs. Peer Models
Shows standard text input and output pricing side by side for each model. If extended-context pricing exists, the chart keeps the base rate and explains the threshold below.
Source: DataLearnerAI. Standard text prices shown here use the default supplier. · USD / 1M tokens
When a context threshold exists, the charted base price only applies within these limits:
| Model | Supplier | Standard input | Standard output | Base price applies to |
|---|---|---|---|---|
Claude Sonnet 5.5 | Anthropic | $2 / 1M tokens | $10 / 1M tokens | — |
GPT-6 Sol | OpenAI | $2 / 1M tokens | $10 / 1M tokens | <= 272000 |
Muse Spark 1.3 | Facebook AI研究实验室 | $1.25 / 1M tokens | $4.25 / 1M tokens | — |
Version History
How each version of the Claude Sonnet 5.5 series stacks up on benchmark tests
12 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.· Click a row to view its trend chart.
| Benchmark | Claude Sonnet 5.5Current | Claude Sonnet 5 | Claude Sonnet 4.6 | Claude Sonnet 4.5 |
|---|---|---|---|---|
64.50Thinking Level · High ｜ Tools | 57.40Thinking Level · Extra High ｜ Tools | 49.00Thinking Enabled ｜ Tools | 33.60Thinking Enabled ｜ Tools | |
66.40Thinking Level · High ｜ Tools | 46.40Thinking Level · High ｜ Tools | 34.50Thinking Level · High ｜ Tools | 31.00Thinking Level · High ｜ Tools | |
71.00Thinking Level · High ｜ Tools | 54.00Deep Thinking Mode ｜ Tools | 29.93Thinking Level · High ｜ Tools | -- | |
81.30Thinking Level · High ｜ Tools | -- | -- | 43.60Thinking Enabled | |
77.75Thinking Level · Extra High | 76.04Thinking Level · Extra High | 75.32Thinking Level · High | 68.1964K | |
77.80Thinking Level · High ｜ Tools | 71.60Thinking Level · High ｜ Tools | -- | -- | |
2.92Thinking Level · High ｜ Tools | 5.00Thinking Level · High ｜ Tools | 5.00Thinking Level · High ｜ Tools | -- | |
48.08Thinking Level · High ｜ Tools | 41.83Thinking Level · High ｜ Tools | 38.46Thinking Level · High ｜ Tools | -- | |
80.49Thinking Level · High ｜ Tools | 29.27Thinking Level · High ｜ Tools | -- | 2.4432K ｜ Tools | |
88.77Thinking Level · High ｜ Tools | 65.61Thinking Level · High ｜ Tools | -- | 23.8632K ｜ Tools | |
55.50Thinking Level · High ｜ Tools | 34.10Thinking Level · High ｜ Tools | -- | -- | |
70.60Thinking Level · High ｜ Tools | 12.42Thinking Level · High ｜ Tools | 3.00Thinking Level · High ｜ Tools | -- |
Single-Benchmark Version Trend
Viewing: HLE · Knowledge Exams
Standard API Pricing Across the Claude Sonnet 5.5 Series
Shows standard text input and output pricing side by side for each model. If extended-context pricing exists, the chart keeps the base rate and explains the threshold below.
Source: DataLearnerAI. Standard text prices shown here use the default supplier. · USD / 1M tokens
When a context threshold exists, the charted base price only applies within these limits:
| Model | Supplier | Standard input | Standard output | Base price applies to |
|---|---|---|---|---|
Claude Sonnet 5.5 | Anthropic | $2 / 1M tokens | $10 / 1M tokens | — |
Claude Sonnet 5 | Anthropic | $2 / 1M tokens | $10 / 1M tokens | — |
Claude Sonnet 4.6 | Anthropic | $3 / 1M tokens | $15 / 1M tokens | — |
Claude Sonnet 4.5 | Anthropic | $3 / 1M tokens | $15 / 1M tokens | <= 200000 |