STEM & Reasoning Benchmark

Apex-Shortlist (with tools)

Apex-Shortlist - with tools variant. Competitive math benchmark with tool use.

Category

STEM & Reasoning

Score type

percent

Scale

100%

higher is better

Models tested

4

What is Apex-Shortlist (with tools)?

Apex-Shortlist (with tools) is a benchmark for hard reasoning in science, technology, engineering and math. The official description says: "Apex-Shortlist - with tools variant". Below we describe in simple words what benchmarks of this type generally examine.

What does it test?

Apex-Shortlist (with tools) 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: Apex-Shortlist - with tools variant. Competitive math benchmark with tool use.

Frequently asked questions

What is the Apex-Shortlist (with tools) benchmark?

Apex-Shortlist (with tools) is a benchmark for hard reasoning in science, technology, engineering and math. The official description says: 'Apex-Shortlist - with tools variant'. Below we describe in simple words what benchmarks of this type generally examine.

What does Apex-Shortlist (with tools) test?

Apex-Shortlist (with tools) 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 Apex-Shortlist (with tools) 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 Apex-Shortlist (with tools) 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/apex-shortlist-with-tools/scores) or pull it directly from the Open LLM Radar API with any HTTP client.

Model scores 4 models tested

Reset
# Model Score Date Source Verified
1 DeepSeek-V4-Pro
DeepSeek
86.5%
04.06.2026 Report Unverified
2 NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
NVIDIA
84.8%
04.06.2026 Report Verified
3 DeepSeek-V4-Flash
DeepSeek
82%
04.06.2026 Report Unverified
4 Kimi K2.6
Moonshot AI
73.2%
04.06.2026 Report Unverified

What now?

You've seen how models score on Apex-Shortlist (with tools) — here's what to do next.