Claude Sonnet 4.6 (Non-reasoning, High Effort)
AnthropicClaudeProprietary
Description
Claude Sonnet 4.6 is a full upgrade of the model's skills across coding, computer use, long-context reasoning, agent planning, knowledge work, and design. Users preferred Sonnet 4.6 over Sonnet 4.5 approximately 70% of the time. First Sonnet-class model with 1M token context window (beta) and context compaction. Major improvement in computer use skills compared to prior Sonnet models. Default model on Free and Pro plans. Pricing: $3/$15 per million tokens (input/output).
Release Date
2026-02-17
Parameters
—
Context Length
1.0M
Modalities
audio, image, pdf, text, video
Capability Radar
22
general
60
coding
80
reasoning
59
science
80
agents
80
multimodal
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Agentic Capability | 13 | 63.0 | LS |
| Code Ranking | 152 | 74.0 | AA |
| General Ranking | 231 | 50.0 | AA |
| Multimodal Ranking | 29 | 60.0 | LS |
| Science | 252 | 51.0 | AA |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))Agents
Finance Agent
63.3%SR
Finance Agent v2
51.0%
Code
DeepSWE 1.1
30.0%
Communication
Tau2 Telecom
97.9%SR
Tau2 Retail
91.7%SR
Language
MMMLU
89.3%SR
Legal
Legal Agent Benchmark
5.4%
Math
LiveBench
75.5%
Multimodal
OSWorld
72.5%SR
Reasoning
GPQANYU + Cohere + Anthropic (2023)
89.9%SR
SWE-Bench Verified
79.6%SR
BrowseCompOpenAI (2025)
74.7%SR
MCP Atlas
61.3%SR
Terminal-Bench 2.0Stanford × Laude Institute (2026)
59.1%SR
ARC-AGI v2
58.3%SR
Humanity's Last Exam
49.0%SR
Vision
MMMU-Pro
75.6%SR
AA Evaluation Indices
(Artificial Analysis)Gpqa(NYU + Cohere + Anthropic (2023))79.9
Tau2(Sierra + U Toronto + Vector Institute (2025))79.5
Lcr(Artificial Analysis)68.3
Terminalbench Hard(Stanford × Laude Institute (2026))46.2
Ifbench(Google Research (2023))41.2
Intelligence Index(Artificial Analysis)24.7
Hle(Center for AI Safety + Scale AI (2025))13.3
LLM Stats Category Scores
(LLM Stats (zeroeval))Language90
Physics90
Biology90
Chemistry90
Communication90
Frontend Development80
Tool Calling80
Math70
Multimodal70
Search70
Reasoning60
Spatial Reasoning60
Finance60
General60
Code60
Vision60
Agents50
Long Context40
Healthcare20
Legal10
Pricing
Input Price$3 / 1M tokens
Output Price$15 / 1M tokens
Blended Price (3:1)$6 / 1M tokens
Cache Read Price$0.3 / 1M tokens
Cache Write Price$3.75 / 1M tokens
Speed
Tokens/sec0.0
Time to First Token0.00s
Time to Answer0.00s
Provider Price Ranking
Provider Price Ranking
2 providers
Cheapest: AnthropicMost Expensive: DeepInfra
ProviderInputOutput
1AnthropicCheapest
$0
$0.00002
2DeepInfra
$0
$0.00002
Compare pricing across different API providers for this model.