Benchmark
APEX-Agents
APEX-Agents is a benchmark evaluating AI agents on long horizon professional tasks that require sustained reasoning, planning, and execution across…
- Modality
- text
- Categories
- reasoning, agents
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 8
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Gemini 3.1 Pro | 0.335 | 2026-02-19 | evidence | |
| Grok 4.6 | xAI | 0.575 | 2026-08-12 | evidence |
| Hy3 | Tencent | 0.256 | 2026-07-06 | evidence |
| Kimi K2.6 | Moonshot AI | 0.279 | 2026-04-20 | evidence |
| Kimi K3 | Moonshot AI | 0.376 | 2026-07-16 | evidence |
| MiniMax M3 | MiniMax | 0.277 | 2026-06-01 | evidence |
| Seed 2.1 Pro | ByteDance | 0.338 | 2026-06-24 | evidence |
| Seed 2.1 Turbo | ByteDance | 0.292 | 2026-06-24 | 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.