AnthropicClaude Sonnet 5 (Adaptive Reasoning, Max Effort)
- Released
- Jun 30, 2026
- Tracked since
- 2026-07-23
Intelligence index38.2Ranks 58 of 664 models with this metric
Coding index71.5Ranks 43 of 259 models with this metric
Agentic index43.6Ranks 33 of 156 models with this metric
Capability profile
5 axes vs. site averageClaude Sonnet 5 (Adaptive Reasoning, Max Effort)
Site average
Pricing
per 1M tokens- Input
- $2.00
- Output
- $10.00
- Cache read
- $0.200
- Cache write
- $2.50
Performance
- Output throughput
- 82 tokens/sec
- Time to first token
- 120.62s
- First answer token
- 120.62s
- End-to-end response
- 126.71s
History
6Intelligence index
53.4→38.2
Output
Unchanged across 62 days of records
Output throughput
84→82
Cheaper at this level
Models with a comparable intelligence index and a lower output price- Qwen3.8-Flash-Next
AlibabaIntelligence 39.8$0.470−95% - GLM 5.3 Flash
Z AIIntelligence 41.8$0.500−95% - GPT-6 Luna (max)
OpenAIIntelligence 37.3$0.500−95% - MiMo-V2.6-Pro
XiaomiIntelligence 46.3$0.870−91% - DeepSeek V4.1 Flash (Reasoning, Max Effort)
DeepSeekIntelligence 39.5$1.20−88%