Quality
#6/7657.3
Overall quality score
🇺🇸AnthropicClosed sourceAnthropic: Claude Opus 4.8.
See how Anthropic: Claude Opus 4.8 compares with other broadly useful AI models across quality, speed, price, context, and practical capabilities.
Speed
#37/7670 t/s
Output tokens per second
Input price
#72/76$5.00/1M
Per 1M tokens
Output price
#71/76$25.00/1M
Per 1M tokens
Context
#12/761M
Content read at once
Comparison summary
Anthropic: Claude Opus 4.8 ranks #6 of 76 for overall quality and #37 for response speed in the current catalogue.
Its listed input price is $5.00/1M, output price is $25.00/1M, and it can work with up to 1M of context at once.
Its strongest areas in the current data are coding, math and logic, following instructions.
Practical specifications
- Company
- Anthropic
- Reasoning
- Yes
- Open weights
- No
- Input
- Text, Image
- Output
- Text
- Context window
- 1M
Anthropic: Claude Opus 4.8 technical benchmarks.
Named evaluation records for technical comparison. Results retain their original benchmark names and sources.
| Benchmark | Area | Claude Opus 4.8 | Source |
|---|---|---|---|
| Intelligence Index | overallQuality | 57.3 | OpenRouter / artificial-analysis |
| Coding Index | coding | 74.3 | OpenRouter / artificial-analysis |
| Agentic Index | agentic | 49.4 | OpenRouter / artificial-analysis |
| GPQA | GPQA Diamond | 92 | OpenRouter model benchmarks |
| Humanity's Last Exam | HLE | 48.7 | OpenRouter model benchmarks |
| IFBench | IFBench | 62.2 | OpenRouter model benchmarks |
| τ²-Bench Telecom | τ²-Bench Telecom | 94.4 | OpenRouter model benchmarks |
| AA-LCR | AA-LCR | 73 | OpenRouter model benchmarks |
| GDPval-AA | GDPval-AA | 54.3 | OpenRouter model benchmarks |
| CritPt | CritPt | 20.9 | OpenRouter model benchmarks |
| SciCode | SciCode | 53.5 | OpenRouter model benchmarks |
| Terminal-Bench Hard | Terminal-Bench Hard | 58.3 | OpenRouter model benchmarks |
| AA-Omniscience Accuracy | AA-Omniscience Accuracy | 48.8 | OpenRouter model benchmarks |
| AA-Omniscience Non-Hallucination Rate | AA-Omniscience Non-Hallucination Rate | 60.7 | OpenRouter model benchmarks |
Quality benchmarks
See where Anthropic: Claude Opus 4.8 stands.
The darker bar marks Anthropic: Claude Opus 4.8; the lighter bars provide context from other leading models.
Highlights
Quality
Overall capability · Higher is better
Speed
Output tokens per second · Higher is better
Input price
USD per 1M tokens · Lower is better