LCB-Pro 25Q2 (Medium)
LiveCodeBench Pro 25Q2 (Medium) - competitive programming evaluation, medium difficulty subset of LCB-Pro 2025 Q2.
Category
STEM & Reasoning
Score type
percent
Scale
100%
higher is better
Models tested
9
What is LCB-Pro 25Q2 (Medium)?
LCB-Pro 25Q2 (Medium) is a benchmark for hard reasoning in science, technology, engineering and math. The official description says: "LiveCodeBench Pro 25Q2 (Medium) - competitive programming evaluation, medium difficulty subset of LCB-Pro 2025 Q2". Below we describe in simple words what benchmarks of this type generally examine.
What does it test?
LCB-Pro 25Q2 (Medium) measures hard reasoning in science, technology, engineering and math. In detail, it checks:
- graduate- and expert-level questions in science and math
- multi-step derivations where each step must be correct
- problems written to defeat memorisation (novel or recent exam problems)
- correct use of formulas, units and logical inference
How to read the score
The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.
Official methodology note: LiveCodeBench Pro 25Q2 (Medium) - competitive programming evaluation, medium difficulty subset of LCB-Pro 2025 Q2.
Frequently asked questions
What is the LCB-Pro 25Q2 (Medium) benchmark?
LCB-Pro 25Q2 (Medium) is a benchmark for hard reasoning in science, technology, engineering and math. The official description says: 'LiveCodeBench Pro 25Q2 (Medium) - competitive programming evaluation, medium difficulty subset of LCB-Pro 2025 Q2'. Below we describe in simple words what benchmarks of this type generally examine.
What does LCB-Pro 25Q2 (Medium) test?
LCB-Pro 25Q2 (Medium) mainly measures hard reasoning in science, technology, engineering and math. Concretely, it checks: graduate- and expert-level questions in science and math; multi-step derivations where each step must be correct; problems written to defeat memorisation (novel or recent exam problems).
How is the LCB-Pro 25Q2 (Medium) score calculated?
The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better. The declared maximum score of this benchmark is 100.0.
Where do I get LCB-Pro 25Q2 (Medium) data and scores?
The official benchmark page/reference is linked on this page. Every score on Open LLM Radar is also available as open data: download the scores JSON (http://open-llm-radar-api:8000/api/v1/benchmarks/lcb-pro-25q2-medium/scores) or pull it directly from the Open LLM Radar API with any HTTP client.
Benchmark data & downloads
Where to get, inspect and reuse the data behind this benchmark.
Model scores 9 models tested
| # | Model | Score | Date | Source | Verified |
|---|---|---|---|---|---|
| 1 |
MiniCPM5-2B
OpenBMB
|
17.5%
|
— | Report | Verified |
| 2 |
Qwen3.5-4B
Qwen
|
7%
|
— | Report | Verified |
| 3 |
granite-4.2-3B
IBM
|
5.3%
|
— | Report | Verified |
| 4 |
Nemotron-3-Nano-4B
NVIDIA
|
5.3%
|
— | Report | Verified |
| 5 |
Gemma4-E4B
Google
|
1.8%
|
— | Report | Verified |
| 6 |
LFM2.5-2.6B
LiquidAI
|
0%
|
— | Report | Verified |
| 7 |
Qwen3.5-2B
Qwen Team (Alibaba Cloud)
|
0%
|
— | Report | Verified |
| 8 |
Gemma4-E2B
Google
|
0%
|
— | Report | Verified |
| 9 |
LFM2.5-8B-A1B
LiquidAI
|
0%
|
— | Report | Verified |