Claude 4 Sonnet

Claude 4 Sonnet is a non-reasoning model from Anthropic. 13 benchmarks count toward its score, in 6 categories.

availableShows if the model has enough results for an index.
IndexOverall score. 50 is the middle.42.5 ±6.0
CoverageShare of the index weight with results.85%
SpeedOutput tokens per second.40/s
Input / 1MUS dollars per 1M input tokens.$3
Output / 1MUS dollars per 1M output tokens.$15
ContextMaximum tokens in one request.200K
EloLMArena rating and rank.N/A

50 is the middle of the board. The range shows the doubt in the index.

CapabilitiesScore per category. 50 is the middle.

50 is the middle
AgenticMulti-step tasks with tools.
43.6
CodingCode writing and repair.
53.2
ReasoningLogic problems and puzzles.
39.7
MultimodalTasks with images and text.
43.4
KnowledgeFacts and expert knowledge.
38.2
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
35.2
MathMath problems.
N/A

Results

13 counted
BenchmarkThe test name.CategoryThe capability that the test measures.ResultThe score from the publisher.IndexThis result on the index scale.RunThe settings of the run.DateDate of the result.Published byThe source of the result.
Software Engineering Benchmark VerifiedCoding72.7%55.8Carlos E. Jimenez et al.
SWE-bench VerifiedCoding70.8%54.3Moatless Tools1 Sept 2026SWE-bench team
SWE-bench VerifiedCoding68.5%52.5OpenHands26 Feb 2026SWE-bench team
Artificial Analysis GPQA DiamondKnowledge68.3%38.6Artificial Analysis
Artificial Analysis MMMU-ProMultimodal62.4%43.4Artificial Analysis
SWE-bench LiteCoding57.5%52.4SWE-agent11 Sept 2025SWE-bench team
SWE-bench LiteCoding56.7%51.7SWE-agent11 Sept 2025SWE-bench team
τ²-Bench Tool-Agent-User EvaluationAgentic52.3%36.4Victor Barres et al.
Artificial Analysis IFBenchInstruction45.4%35.2Artificial Analysis
Artificial Analysis Long Context ReasoningReasoning44.0%38.7Artificial Analysis
Gert Labs Composite Game BenchmarkAgentic39.7%47.8Gert Labs
SWE-bench MultimodalMultimodal35.0%Refact.ai Agent17 Nov 2025SWE-bench team
Artificial Analysis Omniscience AccuracyKnowledge22.7%42.0Artificial Analysis
JobBenchAgentic18.4%46.8Yuetai Li et al.
Artificial Analysis Intelligence IndexKnowledge16.6%43.2Artificial Analysis
Artificial Analysis Humanity's Last ExamKnowledge4.3%29.2Artificial Analysis
Critical Physics TasksReasoning1.1%40.7Artificial Analysis

13 benchmarks count, from 16 of 17 results. A grey row does not count. Too few models took that benchmark.

Sources

BenchLM benchmark aggregationUsed with attribution; per-benchmark results credited to their original authorsSWE-bench team, collected directlyNo licence stated. The repository publishes submission records for reproducibility and transparency and asks that SWE-bench be cited

Same level, lower price

Qwen3.8-Flash-Next66.4 · Freedots3-note Preview65.5 · FreeApodex 1.1 Mini59.1 · Free

More from Anthropic

Claude Opus 5.582.8Claude Fable 5.181.4Claude Opus 577.9Claude Fable 577.5Claude Opus 4.871.1