Inference
EN
Vals AI

Finance Agent v1.1

Evaluating agents on core financial analyst tasks

ModelsModels with a result.51
Top resultBest result on this benchmark.64.4%Claude Opus 4.7
Top-3 spreadPoints from first to third.3.8 pts
UpdatedDate the source changed the results.4 Jun 2026

Result and cost

50 of 51 results

Results

51 results
#ModelResultThe score from the source.CostUS dollars to run one task.TimeTime to run one task.
01Claude Opus 4.764.4% ±2.8$0.8025 min
02Claude Sonnet 4.663.3% ±2.8$1.446 min
03Muse Spark60.6% ±2.8$0.0637 min
04DeepSeek V4 Pro 042360.4% ±2.8$0.58510 min
05Claude Opus 4.6 (Adaptive)60.0% ±2.8$1.115 min
05GPT-5.560.0% ±2.8$1.3314 min
07Gemini 3.1 Pro Preview59.7% ±2.8$0.8734 min
08Claude Opus 4.5 Thinking58.8% ±2.8$1.503 min
09GPT-5.258.5% ±2.9$0.97810 min
10GLM-5.157.7% ±2.8$0.2928 min
11GPT-5.457.2% ±2.9$1.4111 min
12Kimi K2.657.1% ±2.9$0.49325 min
13GPT-5.155.3% ±2.8$0.47410 min
14Gemini 3 Pro55.2% ±2.8$0.5593 min
15Qwen3.6 Plus54.6% ±2.9$0.1525 min
16Claude Sonnet 4.5 Thinking54.5% ±2.9$1.103 min
16Qwen3.5 Plus Thinking54.5% ±2.9$0.2366 min
18Grok 4.353.8% ±2.8$0.44213 min
19Grok 453.5% ±2.9$1.075 min
20GPT-5.4 mini53.4% ±2.8$0.49215 min
21GLM-5 Thinking53.2% ±2.8$0.5019 min
22Qwen 3.6 Max (preview)52.8% ±2.9$0.58831 min
23Grok 4.1 Fast (Reasoning)52.4% ±2.8$0.0582 min
24Grok 4.20 (Reasoning)52.3%$0.3622 min
25GPT-552.2% ±2.9$0.58615 min
26GPT-5 mini51.9% ±2.9$0.14211 min
27Gemma 4 31B50.8% ±2.9$089 min
28Kimi K2.5 Thinking50.6% ±2.8$0.1794 min
29MiniMax M2.748.4% ±2.8$0.1622 min
30GPT-5.4 nano47.8% ±2.8$0.0135 min
31Gemini 3 Flash Preview47.6% ±2.8$0.3715 min
32Claude Haiku 4.5 Thinking46.9% ±2.8$0.3772 min
33Gemini 3.1 Flash Lite Preview46.1% ±2.8$0.0722 min
33Mistral Medium 3.546.1% ±2.9$1.159 min
33Grok 4 Fast (Reasoning)46.1% ±2.8$0.04759 s
36GLM-4.746.0% ±2.8$0.24410 min
37Qwen3.5 Flash45.6% ±2.8$0.0554 min
38Grok 4.1 Fast Non Reasoning44.4% ±2.7$0.0892 min
39Qwen3 Max44.3% ±2.8$0.8025 min
40Gemini 2.5 Pro41.6% ±2.8$0.34131 min
41MiniMax M2.538.6% ±2.6$0.16523 min
42Kimi K2 Thinking36.6% ±2.6$0.2511 min
43GLM-4.636.5% ±2.8$0.18712 min
44MiniMax M2.133.4% ±2.6$0.11422 min
45GPT-OSS 120B21.5% ±2.2$0.0653 min
46Mistral Large 318.0% ±2.2$0.0862 min
47GPT-4o8.1% ±1.5$0.15831 s
48Command A4.2% ±1.0$2.3410 min
49DeepSeek V3.2 (Thinking)2.3% ±0.8$0.20929 min
50Jamba Large 1.70.4% ±0.4$5.0439 min
51DeepSeek V3.20.0%$0.042 min