Claude Opus 5 Benchmark Details
Claude Opus 5 currently shows benchmark results led by HLE (1 / 172, score 64.70), SWE-bench Verified (1 / 112, score 96), ARC-AGI (1 / 68, score 97.50). This page also compares it with 3 competitor models and 4 predecessor or same-series models, including performance and pricing views when available. 1 source link is attached for reference.
Benchmark Results
Benchmark Results
General Knowledge
5 evaluationsCoding and Software Engineer
4 evaluationsAI Agent - Tool Usage
2 evaluationsProductivity Knowledge
2 evaluationsCompetitor Comparison
Benchmark scores for Claude Opus 5 compared against top models in its class
8 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | Claude Opus 5Current | GPT-5.6 Sol | Kimi K3 | GLM-5.2 |
|---|---|---|---|---|
HLE 综合评估 | 64.70Thinking Level · High ｜ Tools | -- | 56.00Thinking Level · High ｜ Tools | 54.70Thinking Enabled ｜ Tools |
DeepSWE 编程与软件工程 | 68.80Thinking Level · High ｜ Tools | 72.70Thinking Level · Extra High ｜ Tools | 67.50Thinking Level · High ｜ Tools | 44.00Deep Thinking Mode ｜ Tools |
SWE-Bench Pro - Public 编程与软件工程 | 79.20Thinking Level · High ｜ Tools | 64.60Thinking Level · Extra High ｜ Tools | -- | 62.10Thinking Enabled ｜ Tools |
BrowseComp AI Agent - 信息收集 | 90.80Thinking Level · High ｜ Tools | -- | 91.20Thinking Level · High ｜ Tools | -- |
Automation Bench AI Agent - 工具使用 | 26.00Thinking Level · High ｜ Tools | -- | 30.80Thinking Level · High ｜ Tools | -- |
OSWorld 2.0 AI Agent - 工具使用 | 70.57Thinking Level · High ｜ Tools | 62.60Thinking Level · Extra High ｜ Tools | -- | -- |
AA-Briefcase 生产力知识 | 1720.00Thinking Level · High ｜ Tools | -- | 1548.00Thinking Level · High ｜ Tools | -- |
GDPval-AA v2 生产力知识 | 1861.00Thinking Level · High ｜ Tools | -- | 1668.00Thinking Level · High ｜ Tools | -- |
Standard API Pricing: Claude Opus 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.
These models use different currencies or billing units, so the page falls back to raw price values instead of a shared bar chart.
| Model | Supplier | Standard input | Standard output | Base price applies to |
|---|---|---|---|---|
Claude Opus 5 | Anthropic | $5 / 1M tokens | $25 / 1M tokens | — |
GPT-5.6 Sol | OpenAI | $5 / 1M tokens | $30 / 1M tokens | — |
Kimi K3 | Moonshot AI | ¥20 / 1M tokens | ¥100 / 1M tokens | — |
GLM-5.2 | 智谱AI | $1.4 / 1M tokens | $4.4 / 1M tokens | — |
Version History
How each version of the Claude Opus 5 series stacks up on benchmark tests
8 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 Opus 5Current | Claude Opus 4.8 | Opus 4.7 | Claude Opus 4.6 | Opus 4.5 |
|---|---|---|---|---|---|
ARC-AGI 综合评估 | 97.50Thinking Level · Extra High | -- | 93.50Thinking Level · High | 92.00Extended Thinking | 80.00Extended Thinking |
ARC-AGI-2 综合评估 | 90.40Thinking Level · High | -- | 75.80Thinking Level · High | 66.30Extended Thinking | 37.60Extended Thinking |
HLE 综合评估 | 64.70Thinking Level · High ｜ Tools | 57.90Extended Thinking ｜ Tools | 54.70Extended Thinking ｜ Tools | 53.00Extended Thinking ｜ Tools | 43.20Extended Thinking ｜ Tools |
DeepSWE 编程与软件工程 | 68.80Thinking Level · High ｜ Tools | 59.00Deep Thinking Mode ｜ Tools | -- | -- | -- |
SWE-bench Multilingual 编程与软件工程 | 89.50Thinking Level · High ｜ Tools | -- | -- | 72.00Extended Thinking ｜ Tools | -- |
SWE-Bench Pro - Public 编程与软件工程 | 79.20Thinking Level · High ｜ Tools | 69.20Extended Thinking ｜ Tools | 64.30Extended Thinking ｜ Tools | -- | -- |
SWE-bench Verified 编程与软件工程 | 96.00Thinking Level · High ｜ Tools | 88.60Extended Thinking ｜ Tools | 87.60Extended Thinking ｜ Tools | 80.84Extended Thinking ｜ Tools | 80.90Extended Thinking ｜ Tools |
BrowseComp AI Agent - 信息收集 | 90.80Thinking Level · High ｜ Tools | 84.30Thinking Level · High ｜ Tools | 79.30Extended Thinking ｜ Tools | 84.00Thinking Enabled ｜ Tools | -- |
Single-Benchmark Version Trend
Viewing: ARC-AGI · 综合评估
Standard API Pricing Across the Claude Opus 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 Opus 5 | Anthropic | $5 / 1M tokens | $25 / 1M tokens | — |
Claude Opus 4.8 | Anthropic | $5 / 1M tokens | $25 / 1M tokens | — |
Opus 4.7 | Anthropic | $5 / 1M tokens | $25 / 1M tokens | — |
Claude Opus 4.6 | Anthropic | $5 / 1M tokens | $25 / 1M tokens | <= 200K |
Opus 4.5 | Facebook AI研究实验室 | $5 / 1M tokens | $25 / 1M tokens | — |