Claude 3 Opus
Claude 3 Opus has too few ranked results yet to rate it on any capability.
Capability profile
Bars show the model's median result as a share of the leading model's, per capability.
No capability has enough ranked results to rate yet.
Price
$15.00input$75.00outputper million tokens
From Artificial Analysis · All prices
Evidence
59results on52benchmarks
- 26 independently verified
- 5 aggregator
- 27 vendor-reported
- 1 cross-referenced
From 22 sources · latest Oct 8, 2026 · How verification works
Research
2 papers reference Claude 3 OpusClaude 3 Opus benchmark results
59 results on 52 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
0 of 6 ranked benchmarks measured
- 23.50May 10, 2026
- GPQA Diamond48.89Oct 8, 2026gpqa
- Humanity's Last Exam2.75Oct 8, 2026aa_hle
Show 1 more reasoning resultHide 1 reasoning result
- GPQA Diamond50.40Oct 7, 2026GPQA
0 of 10 ranked benchmarks measured
- LiveBench · Coding38.28Aug 23, 2026livebench_coding@2025-04-07
- LiveBench · Coding38.28Jun 17, 2026livebench_coding@2025-04-07
- 7.00May 4, 2026
Show 1 more coding resultHide 1 coding result
- SciCode23.26Sep 4, 2026aa_scicode
0 of 6 ranked benchmarks measured
- MathVista50.50Sep 7, 2026MathVista (testmini)
0 of 3 ranked benchmarks measured
- LiveBench · Instruction Following65.52Aug 23, 2026livebench_instruction_following@2025-04-07
- LiveBench · Instruction Following65.10Jun 17, 2026livebench_instruction_following@2025-04-07
0 of 4 ranked benchmarks measured
- 12.60Sep 1, 2026
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- livebench_language52.73Aug 23, 2026livebench_language@2025-04-07
- 95.60Jul 2, 2026
- 92.40Jul 2, 2026
- livebench_language52.73Jun 17, 2026livebench_language@2025-04-07
- 84.37May 19, 2026
- 92.50May 10, 2026
Show 41 more resultsHide 41 results
- AA Intelligence8.72Oct 8, 2026aa_intelligence_index
- AI2D88.10Sep 7, 2026AI2D (test)
- 99.79May 10, 2026
- ARC-Challenge96.40Oct 7, 2026ARC-C
- Artificial Analysis Coding Index19.53Sep 9, 2026aa_coding_index
- Avg.25.70Aug 24, 2026AVG
- BBH86.80Oct 7, 2026BIG-Bench Hard
- 94.00May 10, 2026
- 98.60Jun 22, 2026
- 1.21Jun 22, 2026
- 79.00Jun 22, 2026
- 0.77Jun 22, 2026
- BIG-Bench Hard 3-shot CoT86.80Sep 7, 2026
- DocVQA (test, ANLS score)89.30Sep 7, 2026
- 83.10Oct 7, 2026
- DROP F1 Score83.10Sep 7, 2026
- GPQA (Diamond) 0-shot CoT50.40Sep 7, 2026
- GPQA (Diamond) Maj@32 5-shot CoT59.50Sep 7, 2026
- 95.00Oct 7, 2026
- 97.44May 10, 2026
- 95.40Oct 7, 2026
- 84.90Oct 7, 2026
- HumanEval 0-shot84.90Sep 7, 2026
- 76.03May 10, 2026
- 60.10Sep 7, 2026
- 20.58May 10, 2026
- 0.00May 10, 2026
- 98.48May 10, 2026
- 90.70Oct 7, 2026
- MGSM 0-shot CoT90.70Sep 7, 2026
- 76.79May 10, 2026
- MMLU86.80Sep 7, 2026MMLU 5-shot
- 85.70Sep 7, 2026
- 88.20Sep 7, 2026
- 68.50Oct 7, 2026
- 59.40Sep 7, 2026
- 35.14May 10, 2026
- 44.05May 10, 2026
- 100.00May 10, 2026
- 4.33May 4, 2026
- 3.79May 4, 2026
Claude 3 Opus: common questions
Who makes Claude 3 Opus?
Claude 3 Opus is made by Anthropic.
When was Claude 3 Opus released?
Claude 3 Opus was released on Mar 4, 2024, according to Artificial Analysis.
How much does Claude 3 Opus cost?
Claude 3 Opus costs $15.00 per million input tokens and $75.00 per million output tokens, according to Artificial Analysis. At a mix of three input tokens to one output token, it costs more than 97% of the 330 priced models we track.
How many benchmarks has Claude 3 Opus been tested on?
We track 59 results for Claude 3 Opus on 52 benchmarks from 22 sources, 26 of them independently verified. The latest was recorded on Oct 8, 2026.
About this record
Where Claude 3 Opus's numbers come from, and every name it appears under.
- Tracked since
- May 2, 2026
- Newest source mention
- Aug 24, 2026
Where the results come from
Verification: 59 scores · 26 independently verified · 5 aggregator-attributed · 1 vendor cross-reference · 27 vendor-reported. How these tiers are assigned
From 22 sources on 9 sites. www-cdn.anthropic.com supplies 18 of them; the 26 independently verified results come from 6 sites. Bars are coloured by trust tier.
- www-cdn.anthropic.com18
- storage.googleapis.com12
- api.llm-stats.com9
- huggingface.co7
- artificialanalysis.ai5
- raw.githubusercontent.com3
- swebench.com3
- epoch.ai1
- simple-bench.com1