Skip to content

Benchmark

Vals Finance Agent (v2)

Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages.

Models measured
78
Scores recorded
78
Sources
2
IQ weight
2.83

Score distribution

48.4%
Mean
51.9%
Median
11.6%
Std dev
31%
10th percentile
59%
90th percentile
9%
Min
9%65.4%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.83 for chat models, measured over 78 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Gemini 4 Argon· Vals AI
Values from 2 sources
65.4%
2Gemini 3.8 Flash· Vals AI
Values from 2 sources
61.4%
3Muse Spark Open· Vals AI61.3%
4Muse Spark 1.2· Vals AI60.6%
5Muse Wonder Full· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
59.1%
6Gemini 3.7 Flash· Vals AI59%
7Muse Spark 1.3· Vals AI58.9%
8Claude Fable 5.1· Vals AI58.9%
9Claude Opus 5· Vals AI58.6%
10Claude Opus 5.5· Vals AI58.6%
11Claude Sonnet 5.5· Vals AI58.1%
12Gemini 3.5 Flash· Vals AI57.9%
13GLM 5.3 Flash· Vals AI57.9%
14MiMo V2.6 Pro· Vals AI57.3%
15Muse Spark 1.1· Vals AI57.2%
16DeepSeek V4.1 Flash 1017· Vals AI57%
17Muse Wonder· Vals AI
Values from 2 sources
56.6%
18Muse Wonder 1.0· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim56.6%
19Claude Fable 5· Vals AI56.3%
20Gemini 3.6 Flash· Vals AI56.3%
21MiMo V2.6 Flash· Vals AI56.3%
22GLM 5.3· Vals AI55.8%
23Hy4 preview· Vals AI55.1%
24GPT-5.6 Luna· Vals AI55%
25Mistral Large 4· Vals AI54.7%
26GPT-5.6 Terra· Vals AI54.4%
27Claude Haiku 5.5· Vals AI54.1%
28Claude Opus 4.8· Vals AI53.9%
29Claude Sonnet 5· Vals AI53.9%
30GPT-5.6 Sol· Vals AI53.8%
31Grok 4.6· Vals AI53.7%
32GPT-6 Astra· Vals AI53.5%
33DeepSeek V4.1 Flash· Vals AI53.5%
34Kimi K3· Vals AI53.1%
35Grok 4.7· Vals AI52.3%
36GPT-6.1 Sol· Vals AI52%
37Ember-1· Vals AI51.9%
38GPT 5.5· Vals AI51.8%
39Claude Opus 4.7· Vals AI51.5%
40Claude Sonnet 4.6· Vals AI51%
41Step 5 Preview· Vals AI50.7%
42Qwen3.8 Max· Vals AI50.6%
43DeepSeek V4 Pro 0813· Vals AI50.4%
44GPT-6 Luna· Vals AI49.9%
45GLM 5.2· Vals AI49.7%
46DeepSeek V4 Flash 0731· Vals AI49.5%
47GPT-6 Sol· Vals AI49.1%
48Qwen 3.8 27B· Vals AI48.6%
49Grok 4.5· Vals AI48.3%
50MiniMax M3· Vals AI48.3%

Showing 1–50 of 78 results.

Data credits: Data by LLM Stats