Tested on 7 benchmarks · BenchGecko score 30.3. Top scores: MMLU (67.9%), Winogrande (50.2%), Dtbench (22.7%).
Unusual and adversarial machine learning challenges. Tests robustness of reasoning about edge cases in ML systems.
Competition-level math from AMC, AIME, and olympiad problems. Level 5 is the hardest tier, requiring creative problem-solving.
Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.
Massive Multitask Language Understanding. 57 subjects from STEM, humanities, and social sciences. The most widely-cited knowledge benchmark.
Commonsense coreference resolution. Tests understanding of pronoun references in ambiguous sentences.
Graduate-level science questions written by PhD experts. Diamond subset contains questions where experts disagree, testing deep understanding.
- Typetext
- ContextN/A
- ReleasedJan 2024
- LicenseProprietary
- Statusbenchmark-only
Frequently Asked Questions
Key facts · as of 2026-04-09
- Claude 3 Sonnet by Anthropic. BenchGecko score 30.3, rank 246 of 312 scored models (normalized average of public benchmark scores).
- List price n/a input · n/a output per 1M tokens (as of 2026-04-09).
How to cite · data as of 2026-04-09
Claude 3 Sonnet · benchmarks, pricing and providers. BenchGecko, data as of 2026-04-09. https://benchgecko.ai/model/claude-3-sonnet
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP