Artificial Analysis' implementation of the APEX-Agents benchmark for long-horizon professional-services agent tasks.
BenchLM mirrors the published score view for APEX-Agents-AA. Gemini 3.5 Flash leads the public snapshot at 47.1% , followed by GPT-5.5 (37.7%) and GPT-5.4 (33.3%). BenchLM does not use these results to rank models overall.
Gemini 3.5 Flash
GPT-5.5
OpenAI
GPT-5.4
OpenAI
The published APEX-Agents-AA snapshot is tightly clustered at the top: Gemini 3.5 Flash sits at 47.1%, while the third row is only 13.8 points behind. The broader top-10 spread is 24.7 points, so the benchmark still separates strong models even when the leaders cluster.
21 models have been evaluated on APEX-Agents-AA. The benchmark falls in the Agentic category. This category carries a 22% weight in BenchLM.ai's overall scoring system. APEX-Agents-AA is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
Year
2026
Tasks
452 professional-services agent tasks
Format
Pass@1
Difficulty
Long-horizon workplace agent tasks
BenchLM stores APEX-Agents-AA as a display-only agentic row. Artificial Analysis reports pass@1 over 452 public APEX-Agents tasks spanning investment banking, management consulting, and corporate law.
Version
APEX-Agents-AA 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Artificial Analysis' implementation of the APEX-Agents benchmark for long-horizon professional-services agent tasks.
Gemini 3.5 Flash by Google currently leads with a score of 47.1% on APEX-Agents-AA.
21 AI models have been evaluated on APEX-Agents-AA on BenchLM.
For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.