math benchmark
HiddenMath Leaderboard
HiddenMath is Google DeepMind's internal mathematical reasoning benchmark featuring novel problems not encountered during model training.
Updated Oct 23, 2026
Models13
Model coverage13
MetricScore
EvidenceB
HiddenMath Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelGO | Score63.00% | Percentile100.00% | Participants13 | EvidenceC | Evaluated |
| Rank02 | ModelGO | Score60.30% | Percentile91.67% | Participants13 | EvidenceC | Evaluated |
| Rank03 | ModelGO | Score55.30% | Percentile83.33% | Participants13 | EvidenceC | Evaluated |
| Rank04 | ModelGO | Score54.50% | Percentile75.00% | Participants13 | EvidenceC | Evaluated |
| Rank05 | ModelGO | Score52.00% | Percentile66.67% | Participants13 | EvidenceC | Evaluated |
| Rank06 | ModelGO | Score47.20% | Percentile58.33% | Participants13 | EvidenceC | Evaluated |
| Rank07 | ModelGO | Score43.00% | Percentile50.00% | Participants13 | EvidenceC | Evaluated |
| Rank08 | ModelGO | Score37.70% | Percentile41.67% | Participants13 | EvidenceC | Evaluated |
| Rank09 | ModelGO | Score37.70% | Percentile33.33% | Participants13 | EvidenceC | Evaluated |
| Rank10 | ModelGO | Score32.80% | Percentile25.00% | Participants13 | EvidenceC | Evaluated |
| Rank11 | ModelGO | Score27.70% | Percentile16.67% | Participants13 | EvidenceC | Evaluated |
| Rank12 | ModelGO | Score27.70% | Percentile8.33% | Participants13 | EvidenceC | Evaluated |
| Rank13 | ModelGO | Score15.80% | Percentile0.00% | Participants13 | EvidenceC | Evaluated |
HiddenMath Highlights
The leading models and scores on this benchmark.
HiddenMath Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for HiddenMath
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is HiddenMath?
What HiddenMath measures and how its scores work.
HiddenMath is a mathematical reasoning benchmark from Google DeepMind that introduces novel problems not encountered during model training.
It measures mathematical reasoning capabilities rather than memorization using the Score metric, reported as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- HiddenMath
- Modality
- text
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about HiddenMath.
Which model scores highest on HiddenMath?
Gemini 2.0 Flash is currently ranked first with 63.00%.
What are the top three models on HiddenMath?
The current leaders are Gemini 2.0 Flash (63.00%), Gemma 3 27B (60.30%), and Gemini 2.0 Flash-Lite (55.30%).
Which HiddenMath model has the lowest official input price?
No matched official input price is currently available.
Which models are fastest among HiddenMath results?
The fastest matched records are Gemini 2.0 Flash (183.00 tok/s via Google), Gemini 1.5 Flash (150.00 tok/s via Google), and Gemini 1.5 Flash 8B (150.00 tok/s via Google).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.