AnthropicClaude Opus 5 (Adaptive Reasoning, High Effort)
- Released
- Jul 24, 2026
- Tracked since
- 2026-07-25
Intelligence index48.1Ranks 16 of 664 models with this metric
Coding index76.5Ranks 15 of 259 models with this metric
Agentic index52.3Ranks 12 of 156 models with this metric
Capability profile
5 axes vs. site averageClaude Opus 5 (Adaptive Reasoning, High Effort)
Site average
Pricing
per 1M tokens- Input
- $5.00
- Output
- $25.00
- Cache read
- $0.500
- Cache write
- $6.25
Performance
- Output throughput
- 58 tokens/sec
- Time to first token
- 13.31s
- First answer token
- 13.31s
- End-to-end response
- 21.93s
History
7Intelligence index
58.9→48.1
Output
Unchanged across 62 days of records
Output throughput
55→58
Cheaper at this level
Models with a comparable intelligence index and a lower output price- MiMo-V2.6-Pro
XiaomiIntelligence 46.3$0.870−97% - Muse Spark 1.3 (max)
MetaIntelligence 48.1$4.25−83% - Grok 4.7 (xhigh)
SpaceXAIIntelligence 46.4$6.00−76% - Grok 4.7 (high)SpaceXAIIntelligence 46.3$6.00−76%
- GPT-6 Sol (max)
OpenAIIntelligence 47.5$10.00−60%