math benchmark
SciCode Leaderboard
SciCode is a research coding benchmark with 338 subproblems from 80 scientific problems across 16 natural science sub-fields.
Updated Sep 5, 2026
Models24
Model coverage24
MetricScore
EvidenceB
SciCode Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelBY | Score59.80% | Percentile100.00% | Participants24 | EvidenceC | Evaluated |
| Rank02 | ModelGO | Score59.00% | Percentile95.65% | Participants24 | EvidenceC | Evaluated |
| Rank03 | ModelBY | Score57.80% | Percentile91.30% | Participants24 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score53.50% | Percentile86.96% | Participants24 | EvidenceC | Evaluated |
| Rank05 | ModelMA | Score52.20% | Percentile82.61% | Participants24 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Score51.30% | Percentile78.26% | Participants24 | EvidenceC | Evaluated |
| Rank07 | ModelTM | Score48.70% | Percentile73.91% | Participants24 | EvidenceC | Evaluated |
| Rank08 | ModelMA | Score48.70% | Percentile69.57% | Participants24 | EvidenceC | Evaluated |
| Rank09 | ModelMA | Score44.80% | Percentile65.22% | Participants24 | EvidenceC | Evaluated |
| Rank10 | ModelNV | Score44.60% | Percentile60.87% | Participants24 | EvidenceC | Evaluated |
| Rank11 | ModelME | Score43.60% | Percentile56.52% | Participants24 | EvidenceC | Evaluated |
| Rank12 | ModelNV | Score42.05% | Percentile52.17% | Participants24 | EvidenceC | Evaluated |
| Rank13 | ModelZA | Score41.70% | Percentile47.83% | Participants24 | EvidenceC | Evaluated |
| Rank14 | ModelMI | Score39.00% | Percentile43.48% | Participants24 | EvidenceC | Evaluated |
| Rank15 | ModelIB | Score38.76% | Percentile39.13% | Participants24 | EvidenceC | Evaluated |
| Rank16 | ModelCO | Score38.20% | Percentile34.78% | Participants24 | EvidenceC | Evaluated |
| Rank17 | ModelCO | Score38.00% | Percentile30.43% | Participants24 | EvidenceC | Evaluated |
| Rank18 | ModelIN | Score38.00% | Percentile26.09% | Participants24 | EvidenceC | Evaluated |
| Rank19 | ModelZA | Score37.30% | Percentile21.74% | Participants24 | EvidenceC | Evaluated |
| Rank20 | ModelIB | Score36.09% | Percentile17.39% | Participants24 | EvidenceC | Evaluated |
| Rank21 | ModelMI | Score36.00% | Percentile13.04% | Participants24 | EvidenceC | Evaluated |
| Rank22 | ModelNV | Score33.30% | Percentile8.70% | Participants24 | EvidenceC | Evaluated |
| Rank23 | ModelNV | Score32.60% | Percentile4.35% | Participants24 | EvidenceC | Evaluated |
| Rank24 | ModelIB | Score24.11% | Percentile0.00% | Participants24 | EvidenceC | Evaluated |
SciCode Highlights
The leading models and scores on this benchmark.
SciCode Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for SciCode
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is SciCode?
What SciCode measures and how its scores work.
SciCode challenges language models to code solutions for scientific problems, including mathematics, physics, chemistry, biology, and materials science.
It measures performance involving knowledge recall, reasoning, and code synthesis, 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
- SciCode
- 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 SciCode.
Which model scores highest on SciCode?
Seed 2.1 Pro is currently ranked first with 59.80%.
What are the top three models on SciCode?
The current leaders are Seed 2.1 Pro (59.80%), Gemini 3.1 Pro (59.00%), and Seed 2.1 Turbo (57.80%).
Which SciCode model has the lowest official input price?
Nemotron 3 Super (120B A12B) has the lowest matched official input price at $0.20 input / $0.80 output per 1M tokens.
Which models are fastest among SciCode results?
The fastest matched records are Mercury 2 (346.33 tok/s via Inception), MiniMax M2.1 (100.00 tok/s via MiniMax), and MiniMax M2 (70.00 tok/s via MiniMax).
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.