Quality
Highest overall scores
- 1
Claude Opus 560.7 - 2Anthropic: Claude Opus 4.855.7
- 3Anthropic: Claude Sonnet 553.4
Anthropic model benchmarks.
Compare Anthropic models across answer quality, coding, complex tasks, speed, price, and context size.
Response speed
Fastest output in this sample
- 1Claude Opus 5 (Fast)112 t/s
- 2Anthropic: Claude Sonnet 596.5 t/s
- 3Claude Opus 563 t/s
Input price
Lowest price per 1M tokens
- 1Anthropic: Claude Sonnet 5$2.00/1M
- 2Claude Opus 5$5.00/1M
- 3Anthropic: Claude Opus 4.8$5.00/1M
Highlights
Quality
Overall capability · Higher is better
Speed
Output tokens per second · Higher is better
Input price
USD per 1M tokens · Lower is better
Quality benchmarks
Compare Anthropic model capability.
Performance and price
Compare practical tradeoffs.
All Anthropic models.
5 models in the current catalogue.
| Model | Links | |||||
|---|---|---|---|---|---|---|
| Claude Opus 5 | 60.7 | 63 t/s | 1M | $5.00 | $25.00 | |
| Anthropic: Claude Opus 4.8 | 55.7 | — | 1M | $5.00 | $25.00 | |
| Anthropic: Claude Sonnet 5 | 53.4 | 96.5 t/s | 1M | $2.00 | $10.00 | |
| Anthropic: Claude Opus 4.8 (Fast) | 0 | — | 1M | $10.00 | $50.00 | |
| Claude Opus 5 (Fast) | 0 | 112 t/s | 1M | $10.00 | $50.00 |
Anthropic technical benchmarks.
Compare named evaluation records available for Anthropic models. Missing results remain blank rather than being estimated.
| Benchmark | Area | Claude Opus 5 | Claude Opus 4.8 | Claude Sonnet 5 | Claude Opus 4.8 (Fast) | Claude Opus 5 (Fast) | Source |
|---|---|---|---|---|---|---|---|
| Intelligence Index | overallQuality | 60.7 | 55.7 | 53.4 | — | — | OpenRouter / artificial-analysis |
| Coding Index | coding | 78 | 74.3 | 71.5 | — | — | OpenRouter / artificial-analysis |
| Agentic Index | agentic | 55.3 | 47.2 | 46.7 | — | — | OpenRouter / artificial-analysis |
| GPQA | GPQA Diamond | 93.2 | 92 | 91.1 | — | — | OpenRouter model benchmarks |
| Humanity's Last Exam | HLE | 52.6 | 45.7 | 39.6 | — | — | OpenRouter model benchmarks |
| AA-LCR | AA-LCR | 70 | 67.7 | 70.7 | — | — | OpenRouter model benchmarks |
| GDPval-AA | GDPval-AA | 68 | 54.6 | 55.1 | — | — | OpenRouter model benchmarks |
| CritPt | CritPt | 29.1 | 20.9 | 16.9 | — | — | OpenRouter model benchmarks |
| SciCode | SciCode | 55.7 | 53.5 | 53.6 | — | — | OpenRouter model benchmarks |
| AA-Omniscience Accuracy | AA-Omniscience Accuracy | 54.2 | 46.6 | 38.3 | — | — | OpenRouter model benchmarks |
| AA-Omniscience Non-Hallucination Rate | AA-Omniscience Non-Hallucination Rate | 49.9 | 64.1 | 62.7 | — | — | OpenRouter model benchmarks |
| IFBench | IFBench | — | 62.2 | — | — | — | OpenRouter model benchmarks |
| τ²-Bench Telecom | τ²-Bench Telecom | — | 94.4 | — | — | — | OpenRouter model benchmarks |
| Terminal-Bench Hard | Terminal-Bench Hard | — | 58.3 | — | — | — | OpenRouter model benchmarks |