Claude Opus 4.8 Benchmark Details
Claude Opus 4.8 currently shows benchmark results led by LiveBench (4 / 115, score 78.79), HLE (8 / 185, score 57.90), SWE-bench Verified (5 / 114, score 88.60). This page also compares it with 4 competitor models and 3 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
6 evaluationsOther
3 evaluationsCoding and Software Engineer
7 evaluationsWriting and Creative Capabilities
1 evaluationsAI Agent - Tool Usage
4 evaluationsMath and Reasoning
2 evaluationsCompetitor Comparison
Benchmark scores for Claude Opus 4.8 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 Opus 4.8Current | GPT-5.5 Pro | Gemini 3.1 Pro Preview | Kimi K2.6 | GPT-5.5 |
|---|---|---|---|---|---|
HLE 综合评估 | 57.90Extended Thinking ｜ Tools | 57.20Thinking Level · Extra High ｜ Tools | 51.40Thinking Level · High ｜ Tools | 54.00Thinking Enabled ｜ Tools | 52.20Thinking Level · High ｜ Tools |
LiveBench 综合评估 | 78.79Deep Thinking Mode | -- | 79.93Thinking Level · High | 72.17Thinking Enabled | 80.71Deep Thinking Mode |
GPQA Diamond 科学与综合推理 | 93.60Thinking Level · High | 93.92Thinking Level · Extra High | 94.30Thinking Level · High | 90.50Thinking Enabled | 94.00Thinking Level · Extra High |
DeepSWE 编程与软件工程 | 59.00Deep Thinking Mode ｜ Tools | -- | 12.00Thinking Level · High ｜ Tools | -- | 67.00Thinking Level · Extra High ｜ Tools |
SWE-Bench Pro - Public 编程与软件工程 | 69.20Extended Thinking ｜ Tools | -- | 54.20Thinking Level · High ｜ Tools | 58.60Thinking Enabled ｜ Tools | 58.60Thinking Level · High ｜ Tools |
SWE-bench Verified 编程与软件工程 | 88.60Extended Thinking ｜ Tools | -- | 80.60Thinking Level · High ｜ Tools | 80.20Thinking Enabled ｜ Tools | -- |
Text Arena (Coding) 编程与软件工程 | 1545.05Standard Mode | -- | 1461.49Standard Mode | -- | 1504.74Thinking Level · Extra High |
WeirdML v2 编程与软件工程 | 82.89Thinking Level · Extra High ｜ Tools | -- | 72.10Standard Mode ｜ Tools | -- | 84.91Thinking Level · Extra High ｜ Tools |
Creative Writing 写作和创作 | 1835.30Standard Mode | -- | 1488.80Standard Mode | 1725.10Standard Mode | 1844.00Standard Mode |
SimpleBench 常识推理 | 64.80Standard Mode | 76.90Standard Mode | 79.60Standard Mode | -- | 69.00Standard Mode |
BrowseComp AI Agent - 信息收集 | 84.30Thinking Level · High ｜ Tools | 90.10Deep Thinking Mode ｜ Tools | 85.90Thinking Level · High ｜ Tools | 83.20Thinking Enabled ｜ Tools | 84.40Thinking Level · High ｜ Tools |
GDPval-AA 生产力知识 | 1890.00Extended Thinking ｜ Tools | 82.30Thinking Level · Extra High | -- | -- | 1769.00Thinking Level · High |
Standard API Pricing: Claude Opus 4.8 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 Opus 4.8 | Anthropic | $5 / 1M tokens | $25 / 1M tokens | — |
GPT-5.5 Pro | OpenAI | $30 / 1M tokens | $180 / 1M tokens | — |
Gemini 3.1 Pro Preview | Google Deep Mind | $2 / 1M tokens | $12 / 1M tokens | <= 200K |
Kimi K2.6 | Facebook AI研究实验室 | $0.95 / 1M tokens | $4 / 1M tokens | — |
GPT-5.5 | OpenAI | $5 / 1M tokens | $30 / 1M tokens | — |
Version History
How each version of the Claude Opus 4.8 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 Opus 4.8Current | Opus 4.7 | Claude Opus 4.6 | Opus 4.5 |
|---|---|---|---|---|
HLE 综合评估 | 57.90Extended Thinking ｜ Tools | 54.70Extended Thinking ｜ Tools | 53.00Extended Thinking ｜ Tools | 43.20Extended Thinking ｜ Tools |
LiveBench 综合评估 | 78.79Deep Thinking Mode | 76.91Deep Thinking Mode | 76.33Thinking Level · High | 75.9664K |
GPQA Diamond 科学与综合推理 | 93.60Thinking Level · High | 94.20Extended Thinking | 91.31Extended Thinking | 87.00Extended Thinking |
SWE-Bench Pro - Public 编程与软件工程 | 69.20Extended Thinking ｜ Tools | 64.30Extended Thinking ｜ Tools | -- | -- |
SWE-bench Verified 编程与软件工程 | 88.60Extended Thinking ｜ Tools | 87.60Extended Thinking ｜ Tools | 80.84Extended Thinking ｜ Tools | 80.90Extended Thinking ｜ Tools |
Text Arena (Coding) 编程与软件工程 | 1545.05Standard Mode | 1562.39Standard Mode | 1555.35Standard Mode | 1512.0032K |
WeirdML v2 编程与软件工程 | 82.89Thinking Level · Extra High ｜ Tools | 76.40Standard Mode ｜ Tools | 77.95Thinking Level · High ｜ Tools | 63.7016K ｜ Tools |
Creative Writing 写作和创作 | 1835.30Standard Mode | 1906.40Standard Mode | 1803.80Standard Mode | 1683.20Standard Mode |
SimpleBench 常识推理 | 64.80Standard Mode | 62.90Standard Mode | 67.60Standard Mode | 62.00Extended Thinking |
BrowseComp AI Agent - 信息收集 | 84.30Thinking Level · High ｜ Tools | 79.30Extended Thinking ｜ Tools | 84.00Thinking Enabled ｜ Tools | -- |
GDPval-AA 生产力知识 | 1890.00Extended Thinking ｜ Tools | -- | 1606.00Extended Thinking ｜ Tools | -- |
MCP-Atlas AI Agent - 工具使用 | 82.20Thinking Level · High ｜ Tools | 79.10Thinking Level · High ｜ Tools | 76.80Thinking Level · High ｜ Tools | 69.80Thinking Level · High ｜ Tools |
Single-Benchmark Version Trend
Viewing: HLE · 综合评估
Standard API Pricing Across the Claude Opus 4.8 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 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 | — |