AnthropicClaude Opus 5 (Adaptive Reasoning, Medium Effort)
- Released
- Jul 24, 2026
- Tracked since
- 2026-07-25
Intelligence index44.8Ranks 27 of 664 models with this metric
Coding index74.3Ranks 31 of 259 models with this metric
Agentic index46.2Ranks 28 of 156 models with this metric
Capability profile
5 axes vs. site averageClaude Opus 5 (Adaptive Reasoning, Medium 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
- 5.91s
- First answer token
- 5.91s
- End-to-end response
- 14.50s
History
7Intelligence index
56.3→44.8
Output
Unchanged across 62 days of records
Output throughput
50→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% - Step 5 Preview
StepFunIntelligence 43.7$2.70−89% - Muse Spark 1.3 (max)
MetaIntelligence 48.1$4.25−83% - Muse Spark 1.3 (xhigh)MetaIntelligence 45.1$4.25−83%
- GLM-5.3 (max)
Z AIIntelligence 44.8$4.40−82%