math benchmark
IMO-AnswerBench
IMO-AnswerBench is a benchmark for evaluating mathematical reasoning capabilities on International Mathematical Olympiad (IMO) problems, focusing on answer generation and verification.
Updated Aug 7, 2026
Published models19
Registry coverage19
MetricScore
EvidenceB
IMO-AnswerBench leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | NV | 92.3% | 100.0% | 19 | C | |
| 2 | ZA | 91.0% | 94.4% | 19 | C | |
| 3 | TE | 90.0% | 88.9% | 19 | C | |
| 4 | AC | 90.0% | 83.3% | 19 | C | |
| 5 | DE | 89.8% | 77.8% | 19 | C | |
| 6 | DE | 88.4% | 72.2% | 19 | C | |
| 7 | MA | 86.0% | 66.7% | 19 | C | |
| 8 | AC | 86.0% | 61.1% | 19 | C | |
| 9 | ST | 85.4% | 55.6% | 19 | C | |
| 10 | ZA | 83.8% | 50.0% | 19 | C | |
| 11 | AC | 83.8% | 44.4% | 19 | C | |
| 12 | ZA | 82.0% | 38.9% | 19 | C | |
| 13 | MA | 81.8% | 33.3% | 19 | C | |
| 14 | AC | 80.9% | 27.8% | 19 | C | |
| 15 | AC | 80.8% | 22.2% | 19 | C | |
| 16 | AC | 78.9% | 16.7% | 19 | C | |
| 17 | MA | 78.6% | 11.1% | 19 | C | |
| 18 | ME | 78.6% | 5.6% | 19 | C | |
| 19 | DE | 78.3% | 0.0% | 19 | C |
Score distribution
Top published rows on the benchmark's original scale.
IMO-AnswerBench highlights
The top published results on this benchmark's own scale.
What is IMO-AnswerBench?
Definition and scoring fields from the benchmark registry.
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. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- IMO-AnswerBench
- Modality
- text
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- imo-answerbench|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
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?
19 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is marked as eligible for the current LLMBoard capability methodology.