Claude Opus 4.5 Thinking

Claude Opus 4.5 Thinking is a reasoning model from Anthropic in the Claude Opus 4.5 family. 19 benchmarks count toward its score, in 7 categories.

availableShows if the model has enough results for an index.
IndexOverall score out of 100.57.9 ±4.2
CoverageShare of the index weight with results.95%
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.200K
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.
61.5
CodingCode writing and repair.
55.4
ReasoningLogic problems and puzzles.
54.9
MultimodalTasks with images and text.
59.9
KnowledgeFacts and expert knowledge.
60.1
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
48.0
MathMath problems.
58.2

Results

19 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.
AIMEMath95.4%58.216 Apr 2026Vals AI
MGSMMultilingual95.2%9 Jan 2026Vals AI
τ²-Bench Tool-Agent-User EvaluationAgentic89.5%63.0Victor Barres et al.
Artificial Analysis MMLU-ProKnowledge89.5%Artificial Analysis
MMLU ProKnowledge87.3%58.01 Sept 2026Vals AI
Artificial Analysis GPQA DiamondKnowledge86.6%57.3Artificial Analysis
GPQA DiamondKnowledge85.9%57.51 Sept 2026Vals AI
LiveCodeBenchCoding83.7%60.41 Sept 2026Vals AI
MMMU ProMultimodal82.9%62.31 Sept 2026Vals AI
Artificial Analysis Long Context ReasoningReasoning77.3%61.7Artificial Analysis
SWE-benchCoding76.4%58.81 Sept 2026Vals AI
Artificial Analysis MMMU-ProMultimodal74.0%57.5Artificial Analysis
Artificial Analysis IFBenchInstruction58.0%48.0Artificial Analysis
Terminal-Bench 1.0Agentic57.5%60.312 Jan 2026Vals AI
Terminal-Bench 2.0Agentic53.9%61.24 Jun 2026Vals AI
Artificial Analysis Omniscience AccuracyKnowledge46.6%71.5Artificial Analysis
Artificial Analysis Humanity's Last ExamKnowledge30.1%57.2Artificial Analysis
Artificial Analysis Intelligence IndexKnowledge29.1%58.8Artificial Analysis
Vibe Code Bench v1.1Coding20.6%50.8OpenHands21 Sept 2026Vals AI
IOI v1Coding20.3%51.49 Aug 2026Vals AI
Critical Physics TasksReasoning4.6%48.0Artificial Analysis

19 benchmarks count, from 19 of 21 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