Transaction Market Reciprocity on Transaction Market ALIGN agents infinite-horizon (test)
1.91Avg Seller RewardDeepSeek-V3.1 Reasoner
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| DeepSeek-V3.1 ReasonerModel Category=Reasoning Models, Agent Framework=ALIGN2026.02 | 1.91 | 2.93 | 14.15 | 99 | 95 | |
| o4-miniModel Category=Reasoning Models, Agent Framework=ALIGN2026.02 | 1.61 | 2.49 | 11.96 | 83 | 72 | |
| Qwen3-235B-InstructModel Category=Reasoning Models, Agent Framework=ALIGN2026.02 | 1.5 | 2.18 | 10.76 | 67 | 62 | |
| DeepSeek-V3.1 ChatModel Category=Chat Models, Agent Framework=ALIGN2026.02 | 1.22 | 2.17 | 9.87 | 71 | 46 | |
| Gemini-2.5-Flash-LiteModel Category=Chat Models, Agent Framework=ALIGN2026.02 | 1.04 | 1.42 | 7.18 | 35 | 20 | |
| GPT-4o-miniModel Category=Chat Models, Agent Framework=ALIGN2026.02 | 0.87 | 1.13 | 5.85 | 13 | 0 | |
| Llama-4-MaverickModel Category=Chat Models, Agent Framework=ALIGN2026.02 | 0.81 | 1.86 | 7.77 | 80 | 35 | |
| Kimi-K2-InstructModel Category=Reasoning Models, Agent Framework=ALIGN2026.02 | 0.76 | 2.33 | 9.03 | 99 | 38 |