Benchmark
Apex Benchmark
What is Apex?
Apex is a challenging frontier reasoning benchmark testing advanced multi-step problem solving across difficult STEM and logical tasks.
- Modality
- text
- Evaluates
- reasoning
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 2
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/apex?top_n=500
Apex results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Nemotron 3 Ultra (550B A55B) | NVIDIA | 0.848 | 2026-06-04 | evidence |
| Qwen3.7-Plus | Qwen | 0.227 | 2026-05-31 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.