Anthropic
Claude Opus 5
ReasoningClosed weights
- Intelligence
- 49.7
- Rank 20 of 751 measured models
- Coding
- 77.0
- Rank 10 of 298 measured models
- Output speed
- 57.1 t/s
- Rank 319 of 411 measured models
- Price/1M
- $10
- Rank 633 of 677 measured models
- Context window
- 1M
- Rank 89 of 1256 measured models
- Cost per task
- $4.88
- Rank 192 of 200 measured models
Claude Opus 5 (Xhigh) scores 49.7 on the Artificial Analysis Intelligence Index, ranking 20th of 751 measured models. The closest models on this index are GPT-6.1 Sol (51.8), Claude Fable 5 (batch) (49.6), and Muse Spark 1.3 (48.1). At $10 per million tokens (3:1 input/output blended price), it is more expensive than GPT-6.1 Sol ($4) and Muse Spark 1.3 ($2). With an output speed of 57.1 t/s, it is about as fast as GPT-6.1 Sol (55.2 t/s), slower than Muse Spark 1.3 (114 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- GPT-6.1 Sol
OpenAI · $4 · 55.2 t/s
51.8+2.1$455.2 t/sCompare - Claude Fable 5 (batch)
Anthropic · — · —
49.6−0.1——Compare - Muse Spark 1.3
Meta · $2 · 114 t/s
48.1−1.6$2114 t/sCompare - GPT-6 Sol
OpenAI · $4 · 102 t/s
47.6−2.1$4102 t/sCompare
