Skip to main content
Radar

Five or fewer confirmed AI changes, with original sources, on mornings when something changed.A free source-linked morning brief.

Start free brief

Finance Agent v2

Vals AI benchmark for realistic financial analyst agent tasks across qualitative analysis, quantitative analysis, market work, comparables, precedents, earnings, disclosure, and modeling.

Data verified 24 confirmed releases in the last 30 daysStart free brief

How BenchLM shows Finance Agent v2

BenchLM mirrors the public Vals AI Finance Agent v2 leaderboard captured from https://www.vals.ai/benchmarks/fabv2 and updated by Vals on August 19, 2026. The snapshot preserves overall scores, uncertainty, latency, cost-per-test metadata, and task-level scores where Vals publishes them.

Finance Agent v2 is display only on BenchLM. Vals proprietary or Vals-hosted aggregate views are useful context, but BenchLM does not use them as weighted ranking inputs or as a replacement for benchmark-native source records.

Snapshot

51 Vals rows11 task viewsprivate datasetTasks: Overall, All-Pass, General Qualitative Analysis, General Quantitative Analysis, Market AnalysisDisplay only

Finance Agent v2 score on Finance Agent v2 — August 19, 2026

We mirror the published finance agent v2 score view for Finance Agent v2. Muse Spark 1.2 leads the public snapshot at 60.6%, followed by Gemini 3.7 Flash (59.0%) and Claude Opus 5 (58.6%). We do not use these results to rank models overall.

51 modelsAgenticCurrentDisplay onlyUpdated August 19, 2026

Finance Agent v2 score table (51 models)

Score
1
Muse Spark 1.2Meta · Closedxhigh reasoning
60.6%
2
Gemini 3.7 FlashGoogle · Closedhigh reasoning
59.0%
3
Claude Opus 5Anthropic · Closed
58.6%
4
Gemini 3.5 FlashGoogle · Closedhigh reasoning
57.9%
5
Muse Spark 1.1Meta · Closedxhigh reasoning
57.2%
6
Claude Fable 5Anthropic · Closed
56.3%
7
Gemini 3.6 FlashGoogle · Closedhigh reasoning
56.3%
8
GPT-5.6 LunaOpenAI · Closedmax reasoning
55.0%
9
GPT-5.6 TerraOpenAI · Closedmax reasoning
54.4%
10
Kimi K3Moonshot AI · Closed
54.4%
11
Claude Opus 4.8Anthropic · Closed
53.9%
12
Claude Sonnet 5Anthropic · Closed
53.9%
13
GPT-5.6 SolOpenAI · Closedmax reasoning
53.8%
14
Grok 4.6xAI · Closedhigh reasoning
53.7%
15
GPT-5.5OpenAI · Closedxhigh reasoning
51.8%
16
Claude Opus 4.7Anthropic · Closed
51.5%
17
Claude Sonnet 4.6Anthropic · Closed
51.0%
18
Qwen3.8 MaxAlibaba · Open weight
50.6%
19
DeepSeek V4 Pro 0813DeepSeek · Closedmax reasoning
50.4%
20
GLM-5.2Z.AI · Open weight
49.7%
21
DeepSeek V4 Flash 0731DeepSeek · Closedhigh reasoning
49.5%
22
Qwen3.8-27BAlibaba · Open weightxhigh reasoning
48.6%
23
Grok 4.5xAI · Closedhigh reasoning
48.3%
24
MiniMax M3MiniMax · Open weight
48.3%
25
Qwen3.7 MaxAlibaba · Closed
47.8%
26
Gemini 3.5 Flash-LiteGoogle · Closedhigh reasoning
47.4%
27
InklingThinking Machines Lab · Open weight0.99 reasoning
46.6%
28
GPT-5.4 miniOpenAI · Closedxhigh reasoning
45.4%
29
Kimi K2.6Moonshot AI · Open weight
44.9%
30
GLM-5.1Z.AI · Open weight
44.8%
31
DeepSeek V4 Pro 0813DeepSeek · Closedmax reasoning
44.1%
32
Gemini 3.1 Pro PreviewGooglehigh reasoning
43.0%
33
Gemini 3 Flash PreviewGooglehigh reasoning
42.6%
34
MiMo-V2.5-ProXiaomi · Closed
41.5%
35
Inkling-SmallThinking Machines Lab · Open weight0.99 reasoning
41.3%
36
Qwen3.6 PlusAlibaba · Closed
40.8%
37
Qwen3.7 PlusAlibaba · Closed
38.2%
38
GPT-5.4 nanoOpenAI · Closedhigh reasoning
38.2%
39
Grok 4.3xAI · Closedhigh reasoning
37.7%
41
MiMo-V2.5Xiaomi · Closed
36.7%
42
35.8%
43
Mistral Medium 3.5Mistral AIhigh reasoning
32.1%
44
Claude Haiku 4.5 ThinkingAnthropic · Closed
31.0%
46
Gemini 3.1 Flash Lite PreviewGooglehigh reasoning
30.0%
48
MiniMax M2.7MiniMax · Open weight
27.9%
49
Laguna M.1Poolside · Closed
25.0%
51
Laguna XS.2Poolside · Open weight
15.6%

The published Finance Agent v2 snapshot places Muse Spark 1.2 first at 60.6%. The third row is 2.0 points behind. The broader top-10 range is 6.2 points, so many of the published results sit in a relatively narrow band.

51 models have been evaluated on Finance Agent v2. The benchmark falls in the Agentic category. This category carries a 22% weight in BenchLM.ai's overall scoring system. Finance Agent v2 is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About Finance Agent v2

Year

2026

Tasks

Financial analyst task categories

Format

Mean score across repeated runs

Difficulty

Professional expert-task agent workflow

Vals reports Finance Agent v2 as a multi-category benchmark with severity-weighted partial credit and repeated runs per model. BenchLM mirrors the public Vals leaderboard as a display-only expert-task benchmark.

BenchLM freshness & provenance

Version

Finance Agent v2 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

FAQ

What does Finance Agent v2 measure?

Vals AI benchmark for realistic financial analyst agent tasks across qualitative analysis, quantitative analysis, market work, comparables, precedents, earnings, disclosure, and modeling.

Which model leads the published Finance Agent v2 snapshot?

Muse Spark 1.2 currently leads the published Finance Agent v2 snapshot with 60.6% finance agent v2 score. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on Finance Agent v2?

The August 19, 2026 contains 51 AI models.

Last updated: August 19, 2026 · mirrored from the public benchmark leaderboard

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.