math benchmark
SAT Math
SAT Math benchmark from AGIEval containing standardized mathematics questions from the College Board SAT examination, designed to evaluate mathematical reasoning capabilities of foundation models using human-centric assessment methods.
Updated Aug 7, 2026
Published models1
Registry coverage1
MetricScore
EvidenceB
SAT Math leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | OP | 89.0% | 100.0% | 1 | C |
SAT Math highlights
The top published results on this benchmark's own scale.
What is SAT Math?
Definition and scoring fields from the benchmark registry.
SAT Math benchmark from AGIEval containing standardized mathematics questions from the College Board SAT examination, designed to evaluate mathematical reasoning capabilities of foundation models using human-centric assessment methods.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- SAT Math
- Modality
- text
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- sat-math|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about SAT Math.
Which model scores highest on SAT Math?
GPT-4 is currently ranked first with 89.0%.
What does SAT Math measure?
SAT Math benchmark from AGIEval containing standardized mathematics questions from the College Board SAT examination, designed to evaluate mathematical reasoning capabilities of foundation models using human-centric assessment methods.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.