VerdictPal
Join

Models / Anthropic

Claude Sonnet 4.6

Claude Sonnet · Released 2026-02-17

Anthropic's February 2026 mid-tier model. Vals Index 60.30% (#3 on the public leaderboard — beats GPT 5.4 Mini and Gemini 3 Flash). SWE-bench Verified 79.6%, ARC-AGI-2 58.3%. 1M context, $3 / $15 per 1M tokens — 5× cheaper than Opus 4.8 on input.

The default for production work that needs Anthropic's voice and tool-use discipline without the Opus 4.8 price tag. SWE-bench Verified 79.6% makes it strong enough for most coding agents.

#11 of 24 on Vals Index · current snapshot
60 Vals Index · 25 benchmark rows · 12 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite64
Context1M
Input / 1M$3.0
Output / 1M$15
Knowledge cutoff2025-12-01
Statusflagship
ClaudePerplexity

Family profile

Best published score in each covered benchmark family.

80/100 avg
Knowledge
91
Reasoning
77
Math
84
Coding
94
Agentic
68
Multimodal
66
Long context
62
Tool use
89
Safety
89
Human preference
79

10 tested benchmark families

Editor's note
Sonnet 4.6 is the workhorse. It leads Anthropic's mid-tier and sits at #3 on Vals — between Opus 4.8 and the GPT 5.4 family. For production agents where Opus 4.8 is overkill, this is the Anthropic pick.
Benchmark placements

Where Claude Sonnet 4.6 places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.

BenchmarkFamilyRankScoreSourceDate
BFCLTool use#1/ 2089Berkeley Function Calling Leaderboard V42026-04-15
MCP AtlasTool use#4/ 1075MCP Atlas leaderboard2026-06-09
MMLUKnowledge#4/ 2291Anthropic Claude 3.7/4.6 model card2026-02-17
HELM SafetySafety#5/ 989Stanford HELM leaderboard2026-02-17
LiveBenchReasoning#5/ 2167LiveBench leaderboard2026-04-15
MMMUMultimodal#5/ 866MMMU leaderboard2026-02-17
HumanEvalCoding#7/ 1594Anthropic Claude 3.7/4.6 model card2026-01-01
ARC-AGIReasoning#8/ 1458ARC Prize semi-private evaluation2026-02-17
LongBench v2Long context#8/ 1953LongBench v2 leaderboard2026-04-01
Vending-Bench 2Agentic#8/ 10Andon Labs Vending-Bench 22026-08-04
LMArena (Chatbot Arena)Human preference#10/ 1379LMArena leaderboard2026-05-25
Vals IndexAgentic#11/ 2360Vals AI — Vals Index2026-06-04
SWE-bench VerifiedCoding#13/ 2380SWE-bench official leaderboard2026-05-30
FrontierMathMath#15/ 1532Epoch AI FrontierMath Tiers 1-3 (v2) CSV2026-08-15
MATHMath#16/ 2584Anthropic Claude 3.7/4.6 model card2026-02-17
MMLU-ProKnowledge#31/ 3978MMLU-Pro HuggingFace leaderboard2026-02-17
Terminal-BenchAgentic#48/ 18468Terminal-Bench 2.0 leaderboard2026-06-09
SciCodeCoding#64/ 18047Artificial Analysis2026-09-01
AA time to first tokenPerformance#99/ 186Artificial Analysis2026-09-01
Artificial Analysis Intelligence IndexReasoning#99/ 18737Artificial Analysis2026-09-01
AA output speedPerformance#100/ 187Artificial Analysis2026-09-01
IFBenchReasoning#120/ 12741Artificial Analysis2026-09-01
AA-LCRLong context#132/ 17962Artificial Analysis2026-09-01
Humanity's Last ExamReasoning#144/ 18013Artificial Analysis2026-09-01
GPQA DiamondReasoning#147/ 18577Artificial Analysis GPQA Diamond evaluation2026-06-09
Family context

The three highest-scoring models with pages in each capability family. Where Claude Sonnet 4.6 shows up, it's highlighted.

KnowledgeClaude Sonnet 4.6 · 91
  1. 1
    GPT 5.5
    91
  2. 2
    Claude Opus 4.8
    91
  3. 3
    Claude Sonnet 4.6
    91
ReasoningClaude Sonnet 4.6 · 77
  1. 1
    Claude Mythos Preview
    95
  2. 2
    Gemini 3.7 Flash
    95
  3. 3
    Grok 4.6
    95
MathClaude Sonnet 4.6 · 84
  1. 1
    OpenAI o3
    99
  2. 2
    GPT-5 (medium)
    99
  3. 3
    GPT-5 (high)
    99
CodingClaude Sonnet 4.6 · 94
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticClaude Sonnet 4.6 · 68
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextClaude Sonnet 4.6 · 62
  1. 1
    Muse Spark 1.2
    83
  2. 2
    Kimi K3
    83
  3. 3
    Gemini 3.5 Flash
    81
Tool useClaude Sonnet 4.6 · 89
  1. 1
    Claude Sonnet 4.6
    89
  2. 2
    GPT 5.5
    87
  3. 3
    Claude Opus 4.8
    87
SafetyClaude Sonnet 4.6 · 89
  1. 1
    Claude Opus 4 (2024-07)
    92
  2. 2
    Claude Opus 4.8
    92
  3. 3
    GPT 5.5
    91
Human preferenceClaude Sonnet 4.6 · 79
  1. 1
    GPT 5.5
    95
  2. 2
    Claude Opus 4.8
    92
  3. 3
    Gemini 3.5 Flash
    91
Newest receipts

Benchmark rows added to the public ledger for Claude Sonnet 4.6 in the last 120 days. Older rows live in the full table below.

15 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context62.33%Artificial Analysis6
AA output speedPerformance0 t/sArtificial Analysis6
AA time to first tokenPerformance0.00sArtificial Analysis6
Artificial Analysis Intelligence IndexReasoning36.8%Artificial Analysis6
Humanity's Last ExamReasoning13.3%Artificial Analysis6
IFBenchReasoning41.16%Artificial Analysis6
SciCodeCoding46.9%Artificial Analysis6
FrontierMathMath32.4%Epoch AI FrontierMath Tiers 1-3 (v2) CSV23
Vending-Bench 2Agentic7204.14Andon Labs Vending-Bench 234
Terminal-BenchAgentic68.4%Terminal-Bench 2.0 leaderboard90
GPQA DiamondReasoning77.2%Artificial Analysis GPQA Diamond evaluation90
MCP AtlasTool use75.4%MCP Atlas leaderboard90
Vals IndexAgentic60.3%Vals AI — Vals Index95
SWE-bench VerifiedCoding79.6%SWE-bench official leaderboard100
LMArena (Chatbot Arena)Human preference1396LMArena leaderboard105
Family coverage

A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.

Knowledge91
Reasoning77
Math84
Coding94
Agentic68
Multimodal66
Long context62
Tool use89
Safety89
Human preference79
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaMiniMaxxAIZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for Claude Sonnet 4.6. Scores link to the original source; gaps mean no public row exists yet.

25 sourced rows

25 of 37 catalog benchmarks have a sourced row for Claude Sonnet 4.6.

Knowledge

Reasoning

Math

Coding

Agentic

Multimodal

Long context

Tool use

Performance

Safety

Human preference

Changelog
  1. Released Claude Sonnet 4.6 — Vals #3 at 60.30%, 1M context, $3 / $15.
Sources