math benchmark
EMMA Leaderboard
EMMA (Enhanced MultiModal reAsoning) is a benchmark for organic multimodal reasoning across mathematics, physics, chemistry, and coding.
Updated Sep 5, 2026
Models2
Model coverage2
MetricScore
EvidenceB
EMMA Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelBY | Score79.30% | Percentile100.00% | Participants2 | EvidenceC | Evaluated |
| Rank02 | ModelBY | Score78.40% | Percentile0.00% | Participants2 | EvidenceC | Evaluated |
EMMA Highlights
The leading models and scores on this benchmark.
EMMA Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for EMMA
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is EMMA?
What EMMA measures and how its scores work.
EMMA (Enhanced MultiModal reAsoning) is a benchmark for organic multimodal reasoning.
It measures reasoning across mathematics, physics, chemistry, and coding, reported as Score in ratio units.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- EMMA
- Modality
- multimodal
- 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 EMMA.
Which model scores highest on EMMA?
Seed 2.1 Pro is currently ranked first with 79.30%.
What are the top three models on EMMA?
The current leaders are Seed 2.1 Pro (79.30%) and Seed 2.1 Turbo (78.40%).
Which EMMA model has the lowest official input price?
No matched official input price is currently available.
Which models are fastest among EMMA results?
No matched runtime record is currently available.
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.