MDL
Claude 3 Opus
Anthropic
Verified against Artificial Analysis · Jul 13, 2026
Capability
48
percentile index
Price /M
$15 / $75
in / out
Context
200K
tokens
Avg score
52.2
9 benchmarks
AA Intelligence
11.8
index
Weights
Closed
Released
Mar 4, 2024
About
Claude 3 Opus is a proprietary model in the Claude 3 family from Anthropic. Benchmarked on 9 evals, averaging 52.2.
proprietarytextvision
Benchmark scores · 9
avg 52.2 — higher is betterThe research behind this model
all papers mentioning it →Statistically Reliable LLM-Based Ranking Evaluation via Prediction-Powered Inference▲ 3 on HF · Jun 3, 2026Qwen2.5-VL Technical Report52 cites · Feb 19, 2025Tulu 3: Pushing Frontiers in Open Language Model Post-Training7 cites · Nov 22, 2024Evolutionary Dynamics of Cooperation in Next-Generation LLM Agent Systems: A Cross-Provider Empirical ExtensionMay 28, 2026Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 SonnetMay 28, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.
Details
PublisherAnthropic
FamilyClaude 3
Parameters—
Licenseproprietary
WeightsClosed
ReleasedMar 4, 2024
Performance & price
Price in / out$15 / $75 per 1M
Blended price$30 / 1M
Coding index19.5
Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →
History
full ledger →Capability over time
Append-only ledger — every observed change to this model's numbers.
API providers
Anthropic200K ctx · $75/M
Artificial Analysis$75/M