APEX-Agents
Progress Over Time
Interactive timeline showing model performance evolution on APEX-Agents
State-of-the-art frontier
Open
Proprietary
APEX-Agents Leaderboard
13 models
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Moonshot AI | — | 1.0M | $2.00 / $10.00 | ||
| 2 |  OpenAI | — | 1.1M | $2.00 / $10.00 | ||
| 3 |  xAI | — | 500K | $2.00 / $6.00 | ||
| 4 | Moonshot AI | 2.8T | 1.0M | $2.85 / $14.25 | ||
| 5 |  Tencent | 770B | — | — | ||
| 6 |  ByteDance | — | — | — | ||
| 7 |  Google | — | 1.0M | $2.00 / $12.00 | ||
| 8 | ByteDance | — | — | — | ||
| 9 |  InclusionAI | 124B | 262K | $0.06 / $0.18 | ||
| 10 | Moonshot AI | 1.0T | 262K | $0.75 / $3.50 | ||
| 11 |  MiniMax | 428B | 1.0M | $0.28 / $1.10 | ||
| 12 | Tencent | 295B | 262K | $0.14 / $0.58 | ||
| 13 | Institute of Foundation Models | 375B | — | — |
Notice missing or incorrect data?
What is APEX-Agents?
APEX-Agents is a benchmark evaluating AI agents on long horizon professional tasks that require sustained reasoning, planning, and execution across complex multi-step workflows.
APEX-Agents is a text benchmark evaluating models on reasoning and agents tasks. LLM Stats tracks 13 models on this benchmark, scored on a 0–1 scale. The current average is 0.4, with the leader at 0.7.
Compare leaders on the best AI for reasoning and best AI for agents leaderboards.
Current leaders
Kimi K3.1 Pro from Moonshot AI currently leads the APEX-Agents leaderboard with a score of 0.672 across 13 evaluated AI models.
FAQ
Common questions about the APEX-Agents benchmark and leaderboard.