LiveCodeBench Pro 25Q2
LiveCodeBench Pro 2025 Q2 aggregate over all difficulty splits. As evaluated on the LFM3-1.7B card: vLLM BF16 at full 262,144-token context, temperature 0.6, top_p 0.95. Aggregate entry, distinct from the LCB-Pro 25Q2 (Easy)/(Medium) split entries.
Category
STEM & Reasoning
Score type
percent
Scale
100%
higher is better
Models tested
1
What is LiveCodeBench Pro 25Q2?
LiveCodeBench Pro 25Q2 is a benchmark for hard reasoning in science, technology, engineering and math. The official description says: "LiveCodeBench Pro 2025 Q2 aggregate over all difficulty splits". Below we describe in simple words what benchmarks of this type generally examine.
What does it test?
LiveCodeBench Pro 25Q2 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 2025 Q2 aggregate over all difficulty splits. As evaluated on the LFM3-1.7B card: vLLM BF16 at full 262,144-token context, temperature 0.6, top_p 0.95. Aggregate entry, distinct from the LCB-Pro 25Q2 (Easy)/(Medium) split entries.
Frequently asked questions
What is the LiveCodeBench Pro 25Q2 benchmark?
LiveCodeBench Pro 25Q2 is a benchmark for hard reasoning in science, technology, engineering and math. The official description says: 'LiveCodeBench Pro 2025 Q2 aggregate over all difficulty splits'. Below we describe in simple words what benchmarks of this type generally examine.
What does LiveCodeBench Pro 25Q2 test?
LiveCodeBench Pro 25Q2 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 LiveCodeBench Pro 25Q2 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 LiveCodeBench Pro 25Q2 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/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.