# cash-management on ten-account cash-management (val) Source: [cash-management on ten-account cash-management (val)]() Collection index: [llms.txt]() Data updated: 2026-06-18T06:12:54.373Z Evaluation of cash-management performance on the validation split of the ten-account cash-management dataset, measured using Reward. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | cash-management | | Dataset (including any stated split) | ten-account cash-management (val) | | Metric | Reward | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 18 of 18 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Reward](): Higher is better; unit: SCALAR. ## Recorded results | Method | Reward | Result date | Report paper | | --- | --- | --- | --- | | Random | 1024.2 | Not recorded | 6a337bc7206542251d7c5233 | | Random | 885.7 | Not recorded | 6a337bc7206542251d7c5233 | | PPO | 677.7 | Not recorded | 6a337bc7206542251d7c5233 | | PPO (Search) | 666.6 | Not recorded | 6a337bc7206542251d7c5233 | | Qwen3-Max | 640.6 | Not recorded | 6a337bc7206542251d7c5233 | | FGR | 624.7 | Not recorded | 6a337bc7206542251d7c5233 | | FGR | 592 | Not recorded | 6a337bc7206542251d7c5233 | | PPO | 559.1 | Not recorded | 6a337bc7206542251d7c5233 | | PPO (Search) | 473.8 | Not recorded | 6a337bc7206542251d7c5233 | | Qwen3-Max | 458.2 | Not recorded | 6a337bc7206542251d7c5233 | | AA-PPO | 447.3 | Not recorded | 6a337bc7206542251d7c5233 | | GLM-4.7 | 441.2 | Not recorded | 6a337bc7206542251d7c5233 | | AA-PPO | 429.7 | Not recorded | 6a337bc7206542251d7c5233 | | Kimi-K2.5 | 427.8 | Not recorded | 6a337bc7206542251d7c5233 | | GLM-4.7 | 364.8 | Not recorded | 6a337bc7206542251d7c5233 | | Kimi-K2.5 | 361.2 | Not recorded | 6a337bc7206542251d7c5233 | | AA-PPO (Search) | 286.7 | Not recorded | 6a337bc7206542251d7c5233 | | AA-PPO (Search) | 268.6 | Not recorded | 6a337bc7206542251d7c5233 | ### Random Reward: 1024.2. Result ID: 6a338c60fbc373592c3026ef. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Benchmark","Interface":"Flat-MDP"}. This record does not assert independent reproduction. ### Random Reward: 885.7. Result ID: 6a338c60fbc373592c3026ee. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Benchmark","Interface":"MMDP"}. This record does not assert independent reproduction. ### PPO Reward: 677.7. Result ID: 6a338c60fbc373592c3026e5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"RL","Interface":"Flat-MDP"}. This record does not assert independent reproduction. ### PPO (Search) Reward: 666.6. Result ID: 6a338c60fbc373592c3026e7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"RL","Interface":"Flat-MDP","Search":"true"}. This record does not assert independent reproduction. ### Qwen3-Max Reward: 640.6. Result ID: 6a338c60fbc373592c3026f5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Direct LLM","Interface":"Flat-MDP"}. This record does not assert independent reproduction. ### FGR Reward: 624.7. Result ID: 6a338c60fbc373592c3026ed. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Benchmark","Interface":"Flat-MDP"}. This record does not assert independent reproduction. ### FGR Reward: 592. Result ID: 6a338c60fbc373592c3026ec. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Benchmark","Interface":"MMDP"}. This record does not assert independent reproduction. ### PPO Reward: 559.1. Result ID: 6a338c60fbc373592c3026e4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"RL","Interface":"MMDP"}. This record does not assert independent reproduction. ### PPO (Search) Reward: 473.8. Result ID: 6a338c60fbc373592c3026e6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"RL","Interface":"MMDP","Search":"true"}. This record does not assert independent reproduction. ### Qwen3-Max Reward: 458.2. Result ID: 6a338c60fbc373592c3026f4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Direct LLM","Interface":"MMDP"}. This record does not assert independent reproduction. ### AA-PPO Reward: 447.3. Result ID: 6a338c60fbc373592c3026e9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"RL","Interface":"Flat-MDP"}. This record does not assert independent reproduction. ### GLM-4.7 Reward: 441.2. Result ID: 6a338c60fbc373592c3026f3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Direct LLM","Interface":"Flat-MDP"}. This record does not assert independent reproduction. ### AA-PPO Reward: 429.7. Result ID: 6a338c60fbc373592c3026e8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"RL","Interface":"MMDP"}. This record does not assert independent reproduction. ### Kimi-K2.5 Reward: 427.8. Result ID: 6a338c60fbc373592c3026f1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Direct LLM","Interface":"Flat-MDP"}. This record does not assert independent reproduction. ### GLM-4.7 Reward: 364.8. Result ID: 6a338c60fbc373592c3026f2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Direct LLM","Interface":"MMDP"}. This record does not assert independent reproduction. ### Kimi-K2.5 Reward: 361.2. Result ID: 6a338c60fbc373592c3026f0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Direct LLM","Interface":"MMDP"}. This record does not assert independent reproduction. ### AA-PPO (Search) Reward: 286.7. Result ID: 6a338c60fbc373592c3026eb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"RL","Interface":"Flat-MDP","Search":"true"}. This record does not assert independent reproduction. ### AA-PPO (Search) Reward: 268.6. Result ID: 6a338c60fbc373592c3026ea. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"RL","Interface":"MMDP","Search":"true"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.