llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeBenchmarksmathAMC_2022_23

math benchmark

AMC_2022_23

American Mathematics Competition problems from the 2022-23 academic year, consisting of multiple-choice mathematics competition problems designed for high school students. These problems require advanced mathematical reasoning, problem-solving strategies, and mathematical knowledge covering topics like algebra, geometry, number theory, and combinatorics. The benchmark is derived from the official AMC competitions sponsored by the Mathematical Association of America.

Updated Aug 7, 2026

Published models6
Registry coverage6
MetricScore
EvidenceB

On this page

  • Ranking
  • Distribution
  • Highlights
  • About
  • FAQ

AMC_2022_23 leaderboard

Sorted by the source-provided rank. Higher score is better according to the registry.

6 rows
Columns

Show columns

1MAMistral Large 3 (675B Instruct 2512 Eagle)Mistral AI52.0%100.0%6CAug 7, 2026
2MAMistral Large 3 (675B Base)Mistral AI52.0%80.0%6CAug 7, 2026
3MAMistral Large 3 (675B Instruct 2512 NVFP4)Mistral AI52.0%60.0%6CAug 7, 2026
4MAMistral Large 3 (675B Instruct 2512)Mistral AI52.0%40.0%6CAug 7, 2026
5GOGemini 1.5 ProGoogle46.4%20.0%6CAug 7, 2026
6GOGemini 1.5 FlashGoogle34.8%0.0%6CAug 7, 2026

Score distribution

Top published rows on the benchmark's original scale.

AMC_2022_23

AMC_2022_23 highlights

The top published results on this benchmark's own scale.

Rank #1Mistral Large 3 (675B Instruct 2512 Eagle)52.0%Rank #2Mistral Large 3 (675B Base)52.0%Rank #3Mistral Large 3 (675B Instruct 2512 NVFP4)52.0%Rank #4Mistral Large 3 (675B Instruct 2512)52.0%

What is AMC_2022_23?

Definition and scoring fields from the benchmark registry.

American Mathematics Competition problems from the 2022-23 academic year, consisting of multiple-choice mathematics competition problems designed for high school students. These problems require advanced mathematical reasoning, problem-solving strategies, and mathematical knowledge covering topics like algebra, geometry, number theory, and combinatorics. The benchmark is derived from the official AMC competitions sponsored by the Mathematical Association of America.

Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.

Family
AMC_2022_23
Modality
text
Primary category
math
Score direction
higher
LLMBoard eligible
No
Evaluation key
amc-2022-23|llm-stats-current

Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.

FAQ

Common questions about AMC_2022_23.

Which model scores highest on AMC_2022_23?

Mistral Large 3 (675B Instruct 2512 Eagle) is currently ranked first with 52.0%.

What does AMC_2022_23 measure?

American Mathematics Competition problems from the 2022-23 academic year, consisting of multiple-choice mathematics competition problems designed for high school students. These problems require advanced mathematical reasoning, problem-solving strategies, and mathematical knowledge covering topics like algebra, geometry, number theory, and combinatorics. The benchmark is derived from the official AMC competitions sponsored by the Mathematical Association of America.

Is a higher score better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

6 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.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai