APEX-Agents
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
The Frontier
Best score over time · one chart, every benchmark
Full rankings
74 models tested · sorted by score
Score distribution
Where models cluster
Correlated benchmarks
Pearson r · original research
Benchmarks that track with APEX-Agents
Pearson correlation across models scored on both benchmarks. Closer to 1 = strongly predictive.
Frequently asked
About APEX-Agents
What does APEX-Agents measure?
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments. 74 AI models have been tested on it. Scores range from 1.1 to 82.4 out of 100.
Which model leads on APEX-Agents?
Gemini 4 Argon from Google DeepMind leads APEX-Agents with a score of 82.4. The median score across 74 tested models is 42.0.
Is APEX-Agents saturated?
No · the top score is 82.4 out of 100 (82%). There is still meaningful room for improvement on APEX-Agents.
Does APEX-Agents predict performance on other benchmarks?
Yes · APEX-Agents scores correlate 0.89 with ARC-AGI-2 across 55 shared models. Models that do well on APEX-Agents tend to do well on ARC-AGI-2.
How often is APEX-Agents data refreshed?
BenchGecko pulls updates daily. New model scores on APEX-Agents appear as soon as they are published by Epoch AI or the model provider.
- Category
- Agent
- Max score
- 100
- Models
- 74
- Updated
- 2026-10-26
Top on APEX-Agents
Gemini 4 Argon · 82.4Claude Sonnet 5.5 · 75.5Claude Opus 5.5 · 73.5DeepSeek V4.1 Flash 1017 · 69.8Claude Fable 5.1 · 68.6More agent benchmarks
Same category · related evaluations