AnthropicClaude Sonnet 4.6 (Adaptive Reasoning, Max Effort)
- Released
- Feb 17, 2026
- Tracked since
- 2026-07-23
Intelligence index30.1Ranks 97 of 664 models with this metric
Coding index63Ranks 71 of 259 models with this metric
Agentic index31.8Ranks 60 of 156 models with this metric
Capability profile
5 axes vs. site averageClaude Sonnet 4.6 (Adaptive Reasoning, Max Effort)
Site average
Pricing
per 1M tokens- Input
- $3.00
- Output
- $15.00
- Cache read
- $0.300
- Cache write
- $3.75
Performance
- Output throughput
- 55 tokens/sec
- Time to first token
- 118.27s
- First answer token
- 118.27s
- End-to-end response
- 127.43s
History
6Intelligence index
47.2→30.1
Output
Unchanged across 62 days of records
Output throughput
54→55
Cheaper at this level
Models with a comparable intelligence index and a lower output price- Qwen3.8-Flash-Next
AlibabaIntelligence 39.8$0.470−97% - GLM 5.3 Flash
Z AIIntelligence 41.8$0.500−97% - GPT-6 Luna (max)
OpenAIIntelligence 37.3$0.500−97% - GPT-6 Luna (xhigh)OpenAIIntelligence 33.9$0.500−97%
- GPT-6 Luna (high)OpenAIIntelligence 32.1$0.500−97%