Claude Opus 4.5 Thinking 64K

Claude Opus 4.5 Thinking 64K is a model from Anthropic. 6 benchmarks count toward its score, in 6 categories.

partialShows if the model has enough results for an index.
IndexOverall score out of 100.Unranked
CoverageShare of the index weight with results.85%
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.
54.1
CodingCode writing and repair.
69.9
ReasoningLogic problems and puzzles.
63.3
MultimodalTasks with images and text.
N/A
KnowledgeFacts and expert knowledge.
68.6
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
58.9
MathMath problems.
68.7

Results

6 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.
LiveBench MathematicsMath90.4%68.7high effort25 Jun 2026LiveBench
LiveBench LanguageKnowledge81.3%68.6high effort25 Jun 2026LiveBench
LiveBench ReasoningReasoning80.1%67.2high effort25 Jun 2026LiveBench
LiveBench CodingCoding79.7%69.9high effort25 Jun 2026LiveBench
LiveBench Data AnalysisReasoning74.4%59.4high effort25 Jun 2026LiveBench
LiveBench Instruction FollowingInstruction62.5%58.9high effort25 Jun 2026LiveBench
LiveBench Agentic CodingAgentic39.7%54.1high effort25 Jun 2026LiveBench

6 benchmarks count, from 7 of 7 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 authorsLiveBench, collected directlyNo licence stated for the leaderboard. The site repo serving these CSVs has no LICENSE; the harness repo carries upstream Apache-2.0 and MIT copies that cover code, not results

More from Anthropic

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