Numerical Reasoning on TaTQA
92.9AccuracyGPT-5 mini-high
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GPT-5 mini-highReasoning Capability=with Reasoning, Domain Focus=General2026.03 | 92.9 | 77.1 | |
| Gemini 2.5 Flash-LiteReasoning Capability=with Reasoning, Domain Focus=General2026.03 | 90 | 67.7 | |
| ODA-Fin-RL-8BDomain Focus=Financial2026.03 | 89.3 | 74.6 | |
| Qwen3-4B-ThinkingReasoning Capability=with Reasoning, Domain Focus=General2026.03 | 87.6 | 72.5 | |
| Qwen3-8BReasoning Capability=without Reasoning, Domain Focus=General2026.03 | 87.1 | 71.5 | |
| ODA-Fin-SFT-8BDomain Focus=Financial2026.03 | 87 | 72.1 | |
| Qwen3-32BReasoning Capability=without Reasoning, Domain Focus=General2026.03 | 85.1 | 74.7 | |
| Dianjin-R1-7BDomain Focus=Financial2026.03 | 82 | 70.3 | |
| Qwen2.5-7B-InstructReasoning Capability=without Reasoning, Domain Focus=General2026.03 | 81.5 | 68 | |
| Fin-R1Domain Focus=Financial2026.03 | 80 | 61.4 | |
| Qwen2.5-7BReasoning Capability=without Reasoning, Domain Focus=General2026.03 | 78.3 | 47.8 | |
| Llama-3.1-8B-InstructReasoning Capability=without Reasoning, Domain Focus=General2026.03 | 69.3 | 56.9 | |
| Xuanyuan-6B-ChatDomain Focus=Financial2026.03 | 49.3 | 36.7 | |
| Plutus-8B-InstructDomain Focus=Financial2026.03 | 29.4 | 36.2 |