Finance Agent v2
Results
26 of 41 tracked models have a result.
- 1Gemini 4 ArgonLimited
Google DeepMind · High effort
65.4% - 2
Google DeepMind · High effort
61.4% - 3
Meta · Max effort
60.0% - 4
Anthropic · Max effort
58.9% - 5
Anthropic · Max effort
58.6% - 6
Anthropic · Max effort
58.1% - 7MiMo-V2.6-ProOpen
Xiaomi
57.3% - 8MiMo-V2.6-FlashOpen
Xiaomi
56.3% - 9GLM-5.3Open
Z.ai · Max effort
55.8% - 10Hy4 previewOpen
Tencent
55.1% - 11
Mistral AI · High effort
54.7% - 12
OpenAI · Max effort
54.4% - 13
Anthropic · Max effort
54.1% - 14
OpenAI · Max effort
53.5% - 15
DeepSeek · High effort
53.5% - 16Kimi K3Open
Moonshot AI · Max effort
53.1% - 17
SpaceXAI · xHigh effort
52.3% - 18
OpenAI · Max effort
52.0% - 19
StepFun
50.7% - 20
Alibaba
50.6% - 21DeepSeek V4 ProOpen
DeepSeek · Max effort
50.4% - 22
OpenAI · Max effort
49.9% - 23MiniMax-M3Open
MiniMax
48.3% - 24InklingOpen
Thinking Machines Lab
46.6% - 25
Google DeepMind · High effort
43.0% - 26Inkling-SmallOpen
Thinking Machines Lab
41.3%
15 tracked models without a result
Command A+, Gemini 3.5 Flash-Lite, Gemma 4 31B, GLM-5.3-Flash, gpt-oss-120b, Hy3, Kimi K2.7 Code, MAI-Thinking-1, Mistral Medium 3.5, Mistral Small 4, Muse Glimmer 30B, Nemotron 3 Ultra, Nova 2 Lite, Qwen3.8-27B, Qwen3.8-Flash.
Missing means the evaluator has not published a run, not that the model would score poorly.