math benchmark
AIME 2025 Leaderboard
All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
Updated Aug 17, 2026
Models100
Model coverage115
MetricScore
EvidenceC
AIME 2025 Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelGO | Score100.0% | Percentile100.0% | Participants115 | EvidenceC | Evaluated |
| Rank02 | ModelOP | Score100.0% | Percentile99.1% | Participants115 | EvidenceC | Evaluated |
| Rank03 | ModelOP | Score100.0% | Percentile98.3% | Participants115 | EvidenceC | Evaluated |
| Rank04 | ModelXA | Score100.0% | Percentile97.4% | Participants115 | EvidenceC | Evaluated |
| Rank05 | ModelMA | Score100.0% | Percentile96.5% | Participants115 | EvidenceC | Evaluated |
| Rank06 | ModelAN | Score99.8% | Percentile95.6% | Participants115 | EvidenceC | Evaluated |
| Rank07 | ModelGO | Score99.7% | Percentile94.7% | Participants115 | EvidenceC | Evaluated |
| Rank08 | ModelOP | Score99.6% | Percentile93.9% | Participants115 | EvidenceC | Evaluated |
| Rank09 | ModelME | Score99.6% | Percentile93.0% | Participants115 | EvidenceC | Evaluated |
| Rank10 | ModelNV | Score99.2% | Percentile92.1% | Participants115 | EvidenceC | Evaluated |
| Rank11 | ModelOP | Score98.7% | Percentile91.2% | Participants115 | EvidenceC | Evaluated |
| Rank12 | ModelOP | Score98.4% | Percentile90.3% | Participants115 | EvidenceC | Evaluated |
| Rank13 | ModelBY | Score98.3% | Percentile89.5% | Participants115 | EvidenceC | Evaluated |
| Rank14 | ModelST | Score97.3% | Percentile88.6% | Participants115 | EvidenceC | Evaluated |
| Rank15 | ModelMI | Score97.0% | Percentile87.7% | Participants115 | EvidenceC | Evaluated |
| Rank16 | ModelOP | Score96.7% | Percentile86.8% | Participants115 | EvidenceC | Evaluated |
| Rank17 | ModelSA | Score96.7% | Percentile86.0% | Participants115 | EvidenceC | Evaluated |
| Rank18 | ModelSA | Score96.7% | Percentile85.1% | Participants115 | EvidenceC | Evaluated |
| Rank19 | ModelMA | Score96.1% | Percentile84.2% | Participants115 | EvidenceC | Evaluated |
| Rank20 | ModelDE | Score96.0% | Percentile83.3% | Participants115 | EvidenceC | Evaluated |
| Rank21 | ModelZA | Score95.7% | Percentile82.5% | Participants115 | EvidenceC | Evaluated |
| Rank22 | ModelOP | Score94.6% | Percentile81.6% | Participants115 | EvidenceC | Evaluated |
| Rank23 | ModelOP | Score94.6% | Percentile80.7% | Participants115 | EvidenceC | Evaluated |
| Rank24 | ModelXI | Score94.1% | Percentile79.8% | Participants115 | EvidenceC | Evaluated |
| Rank25 | ModelOP | Score94.0% | Percentile79.0% | Participants115 | EvidenceC | Evaluated |
| Rank26 | ModelOP | Score94.0% | Percentile78.1% | Participants115 | EvidenceC | Evaluated |
| Rank27 | ModelOP | Score94.0% | Percentile77.2% | Participants115 | EvidenceC | Evaluated |
| Rank28 | ModelZA | Score93.9% | Percentile76.3% | Participants115 | EvidenceC | Evaluated |
| Rank29 | ModelXA | Score93.3% | Percentile75.4% | Participants115 | EvidenceC | Evaluated |
| Rank30 | ModelDE | Score93.1% | Percentile74.6% | Participants115 | EvidenceC | Evaluated |
| Rank31 | ModelDE | Score93.1% | Percentile73.7% | Participants115 | EvidenceC | Evaluated |
| Rank32 | ModelBY | Score93.0% | Percentile72.8% | Participants115 | EvidenceC | Evaluated |
| Rank33 | ModelLA | Score92.8% | Percentile71.9% | Participants115 | EvidenceC | Evaluated |
| Rank34 | ModelOP | Score92.7% | Percentile71.0% | Participants115 | EvidenceC | Evaluated |
| Rank35 | ModelOP | Score92.5% | Percentile70.2% | Participants115 | EvidenceC | Evaluated |
| Rank36 | ModelAM Nova 2 ProAmazon | Score92.3% | Percentile69.3% | Participants115 | EvidenceC | Evaluated |
| Rank37 | ModelAC | Score92.3% | Percentile68.4% | Participants115 | EvidenceC | Evaluated |
| Rank38 | ModelAMNova 2 OmniAmazon | Score92.1% | Percentile67.5% | Participants115 | EvidenceC | Evaluated |
| Rank39 | ModelXA | Score92.0% | Percentile66.7% | Participants115 | EvidenceC | Evaluated |
| Rank40 | ModelXA | Score91.7% | Percentile65.8% | Participants115 | EvidenceC | Evaluated |
| Rank41 | ModelZA | Score91.6% | Percentile64.9% | Participants115 | EvidenceC | Evaluated |
| Rank42 | ModelOP | Score91.1% | Percentile64.0% | Participants115 | EvidenceC | Evaluated |
| Rank43 | ModelIN | Score91.1% | Percentile63.2% | Participants115 | EvidenceC | Evaluated |
| Rank44 | ModelAMNova 2 LiteAmazon | Score91.0% | Percentile62.3% | Participants115 | EvidenceC | Evaluated |
| Rank45 | ModelXA | Score90.8% | Percentile61.4% | Participants115 | EvidenceC | Evaluated |
| Rank46 | ModelME | Score90.6% | Percentile60.5% | Participants115 | EvidenceC | Evaluated |
| Rank47 | ModelNV | Score90.2% | Percentile59.6% | Participants115 | EvidenceC | Evaluated |
| Rank48 | ModelCO | Score90.0% | Percentile58.8% | Participants115 | EvidenceC | Evaluated |
| Rank49 | ModelAC | Score89.7% | Percentile57.9% | Participants115 | EvidenceC | Evaluated |
| Rank50 | ModelDE | Score89.3% | Percentile57.0% | Participants115 | EvidenceC | Evaluated |
| Rank51 | ModelOP | Score88.9% | Percentile56.1% | Participants115 | EvidenceC | Evaluated |
| Rank52 | ModelGO | Score88.0% | Percentile55.3% | Participants115 | EvidenceC | Evaluated |
| Rank53 | ModelAC | Score87.8% | Percentile54.4% | Participants115 | EvidenceC | Evaluated |
| Rank54 | ModelST | Score87.7% | Percentile53.5% | Participants115 | EvidenceC | Evaluated |
| Rank55 | ModelDE | Score87.5% | Percentile52.6% | Participants115 | EvidenceC | Evaluated |
| Rank56 | ModelAN | Score87.0% | Percentile51.8% | Participants115 | EvidenceC | Evaluated |
| Rank57 | ModelBA | Score87.0% | Percentile50.9% | Participants115 | EvidenceC | Evaluated |
| Rank58 | ModelOP | Score86.4% | Percentile50.0% | Participants115 | EvidenceC | Evaluated |
| Rank59 | ModelMA | Score86.3% | Percentile49.1% | Participants115 | EvidenceC | Evaluated |
| Rank60 | ModelOP | Score85.2% | Percentile48.3% | Participants115 | EvidenceC | Evaluated |
| Rank61 | ModelMA | Score85.0% | Percentile47.4% | Participants115 | EvidenceC | Evaluated |
| Rank62 | ModelMA | Score83.8% | Percentile46.5% | Participants115 | EvidenceC | Evaluated |
| Rank63 | ModelAC | Score83.7% | Percentile45.6% | Participants115 | EvidenceC | Evaluated |
| Rank64 | ModelAC | Score83.1% | Percentile44.7% | Participants115 | EvidenceC | Evaluated |
| Rank65 | ModelGO | Score83.0% | Percentile43.9% | Participants115 | EvidenceC | Evaluated |
| Rank66 | ModelAC | Score81.6% | Percentile43.0% | Participants115 | EvidenceC | Evaluated |
| Rank67 | ModelAC | Score81.5% | Percentile42.1% | Participants115 | EvidenceC | Evaluated |
| Rank68 | ModelOP | Score81.2% | Percentile41.2% | Participants115 | EvidenceC | Evaluated |
| Rank69 | ModelMI | Score81.0% | Percentile40.4% | Participants115 | EvidenceC | Evaluated |
| Rank70 | ModelAN | Score80.7% | Percentile39.5% | Participants115 | EvidenceC | Evaluated |
| Rank71 | ModelAC | Score80.3% | Percentile38.6% | Participants115 | EvidenceC | Evaluated |
| Rank72 | ModelMA | Score78.7% | Percentile37.7% | Participants115 | EvidenceC | Evaluated |
| Rank73 | ModelOP | Score78.3% | Percentile36.8% | Participants115 | EvidenceC | Evaluated |
| Rank74 | ModelAN | Score78.0% | Percentile36.0% | Participants115 | EvidenceC | Evaluated |
| Rank75 | ModelMI | Score78.0% | Percentile35.1% | Participants115 | EvidenceC | Evaluated |
| Rank76 | ModelMI | Score78.0% | Percentile34.2% | Participants115 | EvidenceC | Evaluated |
| Rank77 | ModelMI | Score76.9% | Percentile33.3% | Participants115 | EvidenceC | Evaluated |
| Rank78 | ModelAN | Score75.5% | Percentile32.5% | Participants115 | EvidenceC | Evaluated |
| Rank79 | ModelAC | Score74.7% | Percentile31.6% | Participants115 | EvidenceC | Evaluated |
| Rank80 | ModelMI | Score74.6% | Percentile30.7% | Participants115 | EvidenceC | Evaluated |
| Rank81 | ModelAC | Score74.5% | Percentile29.8% | Participants115 | EvidenceC | Evaluated |
| Rank82 | ModelAC | Score72.9% | Percentile28.9% | Participants115 | EvidenceC | Evaluated |
| Rank83 | ModelNV | Score72.5% | Percentile28.1% | Participants115 | EvidenceC | Evaluated |
| Rank84 | ModelMA | Score72.1% | Percentile27.2% | Participants115 | EvidenceC | Evaluated |
| Rank85 | ModelNV | Score72.1% | Percentile26.3% | Participants115 | EvidenceC | Evaluated |
| Rank86 | ModelGO | Score72.0% | Percentile25.4% | Participants115 | EvidenceC | Evaluated |
| Rank87 | ModelAC | Score70.9% | Percentile24.6% | Participants115 | EvidenceC | Evaluated |
| Rank88 | ModelAN | Score70.5% | Percentile23.7% | Participants115 | EvidenceC | Evaluated |
| Rank89 | ModelAC | Score70.3% | Percentile22.8% | Participants115 | EvidenceC | Evaluated |
| Rank90 | ModelAC | Score69.5% | Percentile21.9% | Participants115 | EvidenceC | Evaluated |
| Rank91 | ModelAC | Score69.3% | Percentile21.1% | Participants115 | EvidenceC | Evaluated |
| Rank92 | ModelAC | Score66.2% | Percentile20.2% | Participants115 | EvidenceC | Evaluated |
| Rank93 | ModelMA | Score64.9% | Percentile19.3% | Participants115 | EvidenceC | Evaluated |
| Rank94 | ModelME | Score63.2% | Percentile18.4% | Participants115 | EvidenceC | Evaluated |
| Rank95 | ModelMI | Score62.9% | Percentile17.5% | Participants115 | EvidenceC | Evaluated |
| Rank96 | ModelMA | Score62.8% | Percentile16.7% | Participants115 | EvidenceC | Evaluated |
| Rank97 | ModelME | Score61.3% | Percentile15.8% | Participants115 | EvidenceC | Evaluated |
| Rank98 | ModelNV | Score58.4% | Percentile14.9% | Participants115 | EvidenceC | Evaluated |
| Rank99 | ModelAN | Score54.8% | Percentile14.0% | Participants115 | EvidenceC | Evaluated |
| Rank100 | ModelLA | Score51.9% | Percentile13.2% | Participants115 | EvidenceC | Evaluated |
AIME 2025 Highlights
The leading models and scores on this benchmark.
AIME 2025 Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for AIME 2025
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis aime 2025 AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01GOGemini 3 ProGoogle
- Score
- 100.0%
- Speed
- Up to 90 tok/s via Google
Strengths
- Ranks #1 of 115 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures AIME 2025, not total model capability
- 02OPGPT-5.2OpenAI
- Score
- 100.0%
- Price
- $1.8 input / $14 output per 1M tokens
- Speed
- Up to 100 tok/s via OpenAI
Strengths
- Ranks #2 of 115 compared models
- 99th percentile on this benchmark
- C evidence result
Considerations
- This result measures AIME 2025, not total model capability
- 03OPGPT-5.2 ProOpenAI
- Score
- 100.0%
- Price
- $21 input / $168 output per 1M tokens
- Speed
- Up to 25 tok/s via OpenAI
Strengths
- Ranks #3 of 115 compared models
- 98th percentile on this benchmark
- C evidence result
Considerations
- This result measures AIME 2025, not total model capability
- 04XAGrok-4 HeavyxAI
- Score
- 100.0%
Strengths
- Ranks #4 of 115 compared models
- 97th percentile on this benchmark
- C evidence result
Considerations
- This result measures AIME 2025, not total model capability
- 05MAKimi K2-Thinking-0905Moonshot AI
- Score
- 100.0%
- Price
- $0.60 input / $2.5 output per 1M tokens
Strengths
- Ranks #5 of 115 compared models
- 96th percentile on this benchmark
- C evidence result
Considerations
- This result measures AIME 2025, not total model capability
Selection summary
Best AI Models for AIME 2025
Gemini 3 Pro currently leads AIME 2025 with 100.0%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is AIME 2025?
What AIME 2025 measures and how its scores work.
All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of C.
- Family
- AIME 2025
- Modality
- text
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- aime-2025|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about AIME 2025.
Which model scores highest on AIME 2025?
Gemini 3 Pro is currently ranked first with 100.0%.
What does AIME 2025 measure?
All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
100 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.