legal benchmark
AGIEval Leaderboard
AGIEval is a human-centric benchmark with 20 tasks based on standardized academic and professional exams, including college entrance exams, law school admission tests, math competitions, lawyer qualification tests, and civil service exams.
Updated Sep 5, 2026
Models10
Model coverage10
MetricScore
EvidenceB
AGIEval Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMA | Score65.80% | Percentile100.00% | Participants10 | EvidenceC | Evaluated |
| Rank02 | ModelMA | Score64.80% | Percentile88.89% | Participants10 | EvidenceC | Evaluated |
| Rank03 | ModelMA | Score59.10% | Percentile77.78% | Participants10 | EvidenceC | Evaluated |
| Rank04 | ModelNR | Score56.18% | Percentile66.67% | Participants10 | EvidenceC | Evaluated |
| Rank05 | ModelGO | Score55.10% | Percentile55.56% | Participants10 | EvidenceC | Evaluated |
| Rank06 | ModelGO | Score52.80% | Percentile44.44% | Participants10 | EvidenceC | Evaluated |
| Rank07 | ModelMA | Score51.10% | Percentile33.33% | Participants10 | EvidenceC | Evaluated |
| Rank08 | ModelIB | Score49.30% | Percentile22.22% | Participants10 | EvidenceC | Evaluated |
| Rank09 | ModelMA | Score48.30% | Percentile11.11% | Participants10 | EvidenceC | Evaluated |
| Rank10 | ModelBA | Score28.50% | Percentile0.00% | Participants10 | EvidenceC | Evaluated |
AGIEval Highlights
The leading models and scores on this benchmark.
AGIEval Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for AGIEval
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is AGIEval?
What AGIEval measures and how its scores work.
AGIEval evaluates foundation models using 20 tasks, including 18 multiple-choice tasks and 2 cloze tasks, drawn from exams such as Gaokao, SAT, LSAT, math competitions, lawyer qualification tests, and civil service exams.
It assesses understanding, knowledge, reasoning, and calculation abilities in academic and professional contexts, using the Score metric with ratio units.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- AGIEval
- Modality
- text
- Primary category
- legal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about AGIEval.
Which model scores highest on AGIEval?
Mistral Small 3 24B Base is currently ranked first with 65.80%.
What are the top three models on AGIEval?
The current leaders are Mistral Small 3 24B Base (65.80%), Ministral 3 (14B Base 2512) (64.80%), and Ministral 3 (8B Base 2512) (59.10%).
Which AGIEval model has the lowest official input price?
Ministral 3 (14B Base 2512) has the lowest matched official input price at $0.10 input / $0.10 output per 1M tokens.
Which models are fastest among AGIEval results?
The fastest matched records are Ministral 8B Instruct (0.10 tok/s via Mistral AI).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.