Claude 3 Opus

Claude 3 Opus is a non-reasoning model from Anthropic. 11 benchmarks count toward its score, in 4 categories.

availableShows if the model has enough results for an index.
IndexOverall score out of 100.22.6 ±8.9
CoverageShare of the index weight with results.60%
SpeedOutput tokens per second.
Input / 1MUS dollars per 1M input tokens.$15
Output / 1MUS dollars per 1M output tokens.$75
ContextMaximum tokens in one request.200K
EloLMArena rating and rank.1262 (#275)

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

194,909 votes. Elo shows what people prefer. It does not change the score.

CapabilitiesScore per category, out of 100.

Out of 100
AgenticMulti-step tasks with tools.
N/A
CodingCode writing and repair.
15.9
ReasoningLogic problems and puzzles.
30.0
MultimodalTasks with images and text.
N/A
KnowledgeFacts and expert knowledge.
26.9
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
N/A
MathMath problems.
15.7

Results

11 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.
Artificial Analysis GPQA DiamondKnowledge48.9%18.7Artificial Analysis
GPQA diamondKnowledge47.2%21.8Epoch AI
MATH level 5Math37.5%17.1Epoch AI
Artificial Analysis Coding IndexCoding19.5%32.7Artificial Analysis
SimpleQA VerifiedKnowledge12.6%33.2Epoch AI
SWE-bench VerifiedCoding11.4%6.6SWE-agent26 Feb 2026SWE-bench team
SWE-bench VerifiedCoding11.4%6.6RAG baseline1 Sept 2026SWE-bench team
Artificial Analysis Intelligence IndexKnowledge8.7%33.3Artificial Analysis
SWE-bench LiteCoding8.0%10.0SWE-agent11 Sept 2025SWE-bench team
SWE-bench (full test split)Coding7.1%SWE-agent19 Dec 2025SWE-bench team
Chess PuzzlesReasoning5.0%30.0Epoch AI
OTIS Mock AIME 2024-2025Math4.7%14.3Epoch AI
SWE-bench LiteCoding4.3%6.8RAG baseline11 Sept 2025SWE-bench team
Artificial Analysis Humanity's Last ExamKnowledge2.8%27.6Artificial Analysis

11 benchmarks count, from 13 of 14 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 authorsEpoch AI, collected directlyCC BY — free to use and redistribute with attributionSWE-bench team, collected directlyNo licence stated for the leaderboard. The harness repo is MIT

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