math benchmark
IMO-AnswerBench Leaderboard
IMO-AnswerBench is a benchmark for evaluating mathematical reasoning capabilities on International Mathematical Olympiad (IMO) problems, focusing on answer generation and verification.
Updated Aug 17, 2026
Models20
Model coverage20
MetricScore
EvidenceB
IMO-AnswerBench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelNV | Score92.3% | Percentile100.0% | Participants20 | EvidenceC | Evaluated |
| Rank02 | ModelZA | Score91.0% | Percentile94.7% | Participants20 | EvidenceC | Evaluated |
| Rank03 | ModelTE | Score90.0% | Percentile89.5% | Participants20 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score90.0% | Percentile84.2% | Participants20 | EvidenceC | Evaluated |
| Rank05 | ModelDE | Score89.8% | Percentile79.0% | Participants20 | EvidenceC | Evaluated |
| Rank06 | ModelDE | Score88.4% | Percentile73.7% | Participants20 | EvidenceC | Evaluated |
| Rank07 | ModelMA | Score86.0% | Percentile68.4% | Participants20 | EvidenceC | Evaluated |
| Rank08 | ModelAC | Score86.0% | Percentile63.2% | Participants20 | EvidenceC | Evaluated |
| Rank09 | ModelST | Score85.4% | Percentile57.9% | Participants20 | EvidenceC | Evaluated |
| Rank10 | ModelDE | Score85.1% | Percentile52.6% | Participants20 | EvidenceC | Evaluated |
| Rank11 | ModelZA | Score83.8% | Percentile47.4% | Participants20 | EvidenceC | Evaluated |
| Rank12 | ModelAC | Score83.8% | Percentile42.1% | Participants20 | EvidenceC | Evaluated |
| Rank13 | ModelZA | Score82.0% | Percentile36.8% | Participants20 | EvidenceC | Evaluated |
| Rank14 | ModelMA | Score81.8% | Percentile31.6% | Participants20 | EvidenceC | Evaluated |
| Rank15 | ModelAC | Score80.9% | Percentile26.3% | Participants20 | EvidenceC | Evaluated |
| Rank16 | ModelAC | Score80.8% | Percentile21.1% | Participants20 | EvidenceC | Evaluated |
| Rank17 | ModelAC | Score78.9% | Percentile15.8% | Participants20 | EvidenceC | Evaluated |
| Rank18 | ModelMA | Score78.6% | Percentile10.5% | Participants20 | EvidenceC | Evaluated |
| Rank19 | ModelME | Score78.6% | Percentile5.3% | Participants20 | EvidenceC | Evaluated |
| Rank20 | ModelDE | Score78.3% | Percentile0.0% | Participants20 | EvidenceC | Evaluated |
IMO-AnswerBench Highlights
The leading models and scores on this benchmark.
IMO-AnswerBench Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for IMO-AnswerBench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis imo-answerbench 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.
- 01NV
- Score
- 92.3%
- Price
- $0.50 input / $2.5 output per 1M tokens
Strengths
- Ranks #1 of 20 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures IMO-AnswerBench, not total model capability
- 02ZAGLM-5.2Zhipu AI
- Score
- 91.0%
- Price
- $1.4 input / $4.4 output per 1M tokens
Strengths
- Ranks #2 of 20 compared models
- 95th percentile on this benchmark
- C evidence result
Considerations
- This result measures IMO-AnswerBench, not total model capability
- 03TEHy3Tencent
- Score
- 90.0%
Strengths
- Ranks #3 of 20 compared models
- 89th percentile on this benchmark
- C evidence result
Considerations
- This result measures IMO-AnswerBench, not total model capability
- 04ACQwen3.7 MaxAlibaba Cloud / Qwen Team
- Score
- 90.0%
- Price
- $2.5 input / $7.5 output per 1M tokens
- Speed
- Up to 5.8 tok/s via Together
Strengths
- Ranks #4 of 20 compared models
- 84th percentile on this benchmark
- C evidence result
Considerations
- This result measures IMO-AnswerBench, not total model capability
- 05DEDeepSeek-V4-Pro-MaxDeepSeek
- Score
- 89.8%
- Price
- $0.43 input / $0.87 output per 1M tokens
- Speed
- Up to 18 tok/s via Fireworks
Strengths
- Ranks #5 of 20 compared models
- 79th percentile on this benchmark
- C evidence result
Considerations
- This result measures IMO-AnswerBench, not total model capability
Selection summary
Best AI Models for IMO-AnswerBench
Nemotron 3 Ultra (550B A55B) currently leads IMO-AnswerBench with 92.3%. 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 IMO-AnswerBench?
What IMO-AnswerBench measures and how its scores work.
IMO-AnswerBench is a benchmark for evaluating mathematical reasoning capabilities on International Mathematical Olympiad (IMO) problems, focusing on answer generation and verification.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- IMO-AnswerBench
- Modality
- text
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- imo-answerbench|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about IMO-AnswerBench.
Which model scores highest on IMO-AnswerBench?
Nemotron 3 Ultra (550B A55B) is currently ranked first with 92.3%.
What does IMO-AnswerBench measure?
IMO-AnswerBench is a benchmark for evaluating mathematical reasoning capabilities on International Mathematical Olympiad (IMO) problems, focusing on answer generation and verification.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
20 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.