math benchmark
AGIEval
A human-centric benchmark for evaluating foundation models on standardized exams including college entrance exams (Gaokao, SAT), law school admission tests (LSAT), math competitions, lawyer qualification tests, and civil service exams. Contains 20 tasks (18 multiple-choice, 2 cloze) designed to assess understanding, knowledge, reasoning, and calculation abilities in real-world academic and professional contexts.
Updated Aug 7, 2026
Published models10
Registry coverage10
MetricScore
EvidenceB
AGIEval leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | MA | 65.8% | 100.0% | 10 | C | |
| 2 | MA | 64.8% | 88.9% | 10 | C | |
| 3 | MA | 59.1% | 77.8% | 10 | C | |
| 4 | NR | 56.2% | 66.7% | 10 | C | |
| 5 | GO | 55.1% | 55.6% | 10 | C | |
| 6 | GO | 52.8% | 44.4% | 10 | C | |
| 7 | MA | 51.1% | 33.3% | 10 | C | |
| 8 | IB | 49.3% | 22.2% | 10 | C | |
| 9 | MA | 48.3% | 11.1% | 10 | C | |
| 10 | BA | 28.5% | 0.0% | 10 | C |
Score distribution
Top published rows on the benchmark's original scale.
AGIEval highlights
The top published results on this benchmark's own scale.
What is AGIEval?
Definition and scoring fields from the benchmark registry.
A human-centric benchmark for evaluating foundation models on standardized exams including college entrance exams (Gaokao, SAT), law school admission tests (LSAT), math competitions, lawyer qualification tests, and civil service exams. Contains 20 tasks (18 multiple-choice, 2 cloze) designed to assess understanding, knowledge, reasoning, and calculation abilities in real-world academic and professional contexts.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- AGIEval
- Modality
- text
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- agieval|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about AGIEval.
Which model scores highest on AGIEval?
Mistral Small 3 24B Base is currently ranked first with 65.8%.
What does AGIEval measure?
A human-centric benchmark for evaluating foundation models on standardized exams including college entrance exams (Gaokao, SAT), law school admission tests (LSAT), math competitions, lawyer qualification tests, and civil service exams. Contains 20 tasks (18 multiple-choice, 2 cloze) designed to assess understanding, knowledge, reasoning, and calculation abilities in real-world academic and professional contexts.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
10 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is marked as eligible for the current LLMBoard capability methodology.