Claude Sonnet 4 Thinking

Claude Sonnet 4 Thinking is a model from Anthropic. 8 benchmarks count toward its score, in 5 categories.

availableShows if the model has enough results for an index.
IndexOverall score out of 100.47.0 ±8.2
CoverageShare of the index weight with results.75%
SpeedOutput tokens per second.
Input / 1MUS dollars per 1M input tokens.N/A
Output / 1MUS dollars per 1M output tokens.N/A
ContextMaximum tokens in one request.N/A
EloLMArena rating and rank.N/A

The index is a score out of 100. The ± range shows how much it can change.

CapabilitiesScore per category, out of 100.

Out of 100
AgenticMulti-step tasks with tools.
49.7
CodingCode writing and repair.
41.8
ReasoningLogic problems and puzzles.
N/A
MultimodalTasks with images and text.
49.3
KnowledgeFacts and expert knowledge.
50.1
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
N/A
MathMath problems.
47.9

Results

8 counted
BenchmarkThe test name.CategoryThe capability that the test measures.ResultThe score from the publisher.IndexThis result as a score out of 100.RunThe settings of the run.DateDate of the result.Published byThe source of the result.
MATH 500Math93.8%46.69 Jan 2026Vals AI
MGSMMultilingual90.9%9 Jan 2026Vals AI
MMLU ProKnowledge83.9%52.71 Sept 2026Vals AI
AIMEMath76.3%49.316 Apr 2026Vals AI
GPQA DiamondKnowledge75.0%47.51 Sept 2026Vals AI
MMMU ProMultimodal74.9%49.31 Sept 2026Vals AI
LiveCodeBenchCoding62.4%41.11 Sept 2026Vals AI
Terminal-Bench 1.0Agentic45.0%49.712 Jan 2026Vals AI
IOI v1Coding4.6%42.59 Aug 2026Vals AI

8 benchmarks count, from 8 of 9 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 authorsVals AI, collected directlyNo licence stated. Read from the public leaderboard and credited to Vals AI

More from Anthropic

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