Claude 3 Sonnet
Claude 3 Sonnet 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
No current price is tracked for this model. See the rate card
Evidence
48results on41benchmarks
- 18 independently verified
- 4 aggregator
- 26 vendor-reported
From 17 sources · latest Oct 8, 2026 · How verification works
Claude 3 Sonnet benchmark results
48 results on 41 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
- GPQA Diamond40.00Oct 8, 2026gpqa
- Humanity's Last Exam3.62Oct 8, 2026aa_hle
- GPQA Diamond40.40Oct 7, 2026GPQA
0 of 10 ranked benchmarks measured
- LiveBench · Coding27.34Aug 23, 2026livebench_coding@2025-04-07
- LiveBench · Coding27.34Jun 17, 2026livebench_coding@2025-04-07
- SciCode22.92Sep 4, 2026aa_scicode
0 of 6 ranked benchmarks measured
- MathVista47.90Sep 7, 2026MathVista (testmini)
0 of 3 ranked benchmarks measured
- LiveBench · Instruction Following64.83Aug 23, 2026livebench_instruction_following@2025-04-07
- LiveBench · Instruction Following63.62Jun 17, 2026livebench_instruction_following@2025-04-07
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- livebench_language38.37Aug 23, 2026livebench_language@2025-04-07
- 91.80Jul 2, 2026
- 90.70Jul 2, 2026
- livebench_language38.37Jun 17, 2026livebench_language@2025-04-07
- 84.69May 19, 2026
- 85.83May 10, 2026
Show 33 more resultsHide 33 results
- AA Intelligence5.88Oct 8, 2026aa_intelligence_index
- 99.84May 10, 2026
- ARC-Challenge93.20Oct 7, 2026ARC-C
- BBH82.90Oct 7, 2026BIG-Bench Hard
- 90.00May 10, 2026
- 93.60Jun 22, 2026
- 4.95Jun 22, 2026
- 90.40Jun 22, 2026
- 1.22Jun 22, 2026
- BIG-Bench Hard 3-shot CoT82.90Sep 7, 2026
- DocVQA (test, ANLS score)89.50Sep 7, 2026
- 78.90Oct 7, 2026
- DROP F1 Score78.90Sep 7, 2026
- GPQA (Diamond) 0-shot CoT40.40Sep 7, 2026
- GPQA (Diamond) Maj@32 5-shot CoT46.30Sep 7, 2026
- 92.30Oct 7, 2026
- 95.75May 10, 2026
- 89.00Oct 7, 2026
- 73.00Oct 7, 2026
- HumanEval 0-shot73.00Sep 7, 2026
- 8.44May 10, 2026
- 43.10Sep 7, 2026
- 83.50Oct 7, 2026
- MGSM 0-shot CoT83.50Sep 7, 2026
- 65.21May 10, 2026
- MMLU78.30Sep 7, 2026MMLU 5-shot
- 77.10Sep 7, 2026
- 81.50Sep 7, 2026
- 56.80Oct 7, 2026
- 53.10Sep 7, 2026
- 11.14May 10, 2026
- 2.83May 10, 2026
- 100.00May 10, 2026
Claude 3 Sonnet: common questions
Who makes Claude 3 Sonnet?
Claude 3 Sonnet is made by Anthropic.
When was Claude 3 Sonnet released?
Claude 3 Sonnet was released on Mar 4, 2024, according to Artificial Analysis.
How many benchmarks has Claude 3 Sonnet been tested on?
We track 48 results for Claude 3 Sonnet on 41 benchmarks from 17 sources, 18 of them independently verified. The latest was recorded on Oct 8, 2026.
About this record
Where Claude 3 Sonnet's numbers come from, and every name it appears under.
- Tracked since
- Apr 25, 2026
- Newest source mention
- May 18, 2026
Where the results come from
Verification: 48 scores · 18 independently verified · 4 aggregator-attributed · 26 vendor-reported. How these tiers are assigned
From 17 sources on 5 sites. www-cdn.anthropic.com supplies 17 of them; the 18 independently verified results come from 2 sites. Bars are coloured by trust tier.
- www-cdn.anthropic.com17
- storage.googleapis.com12
- api.llm-stats.com9
- huggingface.co6
- artificialanalysis.ai4