List your company

Numerical Reasoning on TaTQA

92.9AccuracyGPT-5 mini-high
26.8644.00561.1578.295Mar 7, 2026

Evaluation results

MethodLinks
GPT-5 mini-highReasoning Capability=with Reasoning, Domain Focus=General2026.0392.977.1
Gemini 2.5 Flash-LiteReasoning Capability=with Reasoning, Domain Focus=General2026.039067.7
ODA-Fin-RL-8BDomain Focus=Financial2026.0389.374.6
Qwen3-4B-ThinkingReasoning Capability=with Reasoning, Domain Focus=General2026.0387.672.5
Qwen3-8BReasoning Capability=without Reasoning, Domain Focus=General2026.0387.171.5
ODA-Fin-SFT-8BDomain Focus=Financial2026.038772.1
Qwen3-32BReasoning Capability=without Reasoning, Domain Focus=General2026.0385.174.7
Dianjin-R1-7BDomain Focus=Financial2026.038270.3
Qwen2.5-7B-InstructReasoning Capability=without Reasoning, Domain Focus=General2026.0381.568
Fin-R1Domain Focus=Financial2026.038061.4
Qwen2.5-7BReasoning Capability=without Reasoning, Domain Focus=General2026.0378.347.8
Llama-3.1-8B-InstructReasoning Capability=without Reasoning, Domain Focus=General2026.0369.356.9
Xuanyuan-6B-ChatDomain Focus=Financial2026.0349.336.7
Plutus-8B-InstructDomain Focus=Financial2026.0329.436.2