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
BenchLM

Vals Finance Agent v1.1 (Finance Agent v1.1)

Evaluates agents on core financial analyst tasks spanning retrieval, numerical reasoning, modeling, and market analysis.

Data verified 28 confirmed releases in the last 30 daysStart free brief

How BenchLM shows Finance Agent v1.1

BenchLM mirrors the public Vals AI Finance Agent v1.1 leaderboard captured from https://www.vals.ai/benchmarks/finance_agent and updated by Vals on June 4, 2026. The snapshot preserves overall scores, uncertainty, latency, cost-per-test metadata, and task-level scores where Vals publishes them.

Finance Agent v1.1 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.

51 Vals rows11 task viewsprivate datasetTasks: Overall, Simple retrieval - Quantitative, Simple retrieval - Qualitative, Complex Retrieval, Numerical ReasoningDisplay only
Finance Agent v1.1 on Vals AIVals methodologyVals home

Finance Agent v1.1 score on Finance Agent v1.1 — June 4, 2026

BenchLM mirrors the published finance agent v1.1 score view for Finance Agent v1.1. Claude Opus 4.7 leads the public snapshot at 64.37% , followed by Claude Sonnet 4.6 (63.33%) and Muse Spark (60.59%). We do not use these results to rank models overall.

1

Claude Opus 4.7

Anthropic

anthropic/claude-opus-4-7

64.37%
Overall —
2

Claude Sonnet 4.6

Anthropic

anthropic/claude-sonnet-4-6

63.33%
Overall —
3

Muse Spark

Meta

meta/muse_spark

60.59%
Overall —
51 modelsExternal benchmark mirrorsCurrentDisplay onlyUpdated June 4, 2026

Finance Agent v1.1 score table (51 models)

Score
1
Claude Opus 4.7Anthropic
64.37%
2
Claude Sonnet 4.6Anthropic
63.33%
3
Muse SparkMeta
60.59%
4
DeepSeek V4 ProDeepSeek
60.39%
5
Claude Opus 4.6 ThinkingAnthropic
60.05%
6
GPT-5.5OpenAI
59.96%
7
Gemini 3.1 Pro PreviewGoogle
59.72%
8
Claude Opus 4.5 20251101 ThinkingAnthropic
58.81%
9
GPT-5.2OpenAI
58.53%
10
GLM 5.1zAI
57.66%
11
GPT-5.4OpenAI
57.15%
12
Kimi K2.6Moonshot AI
57.06%
13
GPT-5.1OpenAI
55.31%
14
Gemini 3 Pro PreviewGoogle
55.15%
15
Qwen3.6 PlusAlibaba
54.63%
16
Claude Sonnet 4.5 20250929 ThinkingAnthropic
54.50%
17
Qwen3.5 Plus ThinkingAlibaba
54.48%
18
Grok 4.3xAI
53.81%
19
Grok 4 0709xAI
53.51%
20
GPT-5.4 MiniOpenAI
53.41%
21
GLM 5 ThinkingzAI
53.18%
22
Qwen3.6 Max PreviewAlibaba
52.78%
23
Grok 4.1 Fast ReasoningxAI
52.45%
24
Grok 4.20 0309 ReasoningxAI
52.30%
25
GPT-5OpenAI
52.15%
26
GPT-5 MiniOpenAI
51.93%
27
Gemma 4 31b ItGoogle
50.79%
28
Kimi K2.5 ThinkingMoonshot AI
50.62%
29
MiniMax M2.7MiniMax
48.40%
30
GPT-5.4 NanoOpenAI
47.80%
31
Gemini 3 Flash PreviewGoogle
47.60%
32
Claude Haiku 4.5 20251001 ThinkingAnthropic
46.93%
33
Gemini 3.1 Flash Lite PreviewGoogle
46.12%
34
Mistral Medium 3.5Mistral
46.11%
35
Grok 4 Fast ReasoningxAI
46.08%
36
GLM 4.7zAI
45.98%
37
Qwen3.5 FlashAlibaba
45.64%
38
Grok 4.1 Fast Non ReasoningxAI
44.36%
39
Qwen3 MaxAlibaba
44.30%
40
Gemini 2.5 ProGoogle
41.59%
41
MiniMax M2.5MiniMax
38.58%
42
Kimi K2 ThinkingMoonshot AI
36.65%
43
GLM 4.6zAI
36.48%
44
MiniMax M2.1MiniMax
33.35%
45
GPT Oss 120bFireworks
21.54%
46
Mistral Large 2512Mistral
18.05%
47
GPT-4oOpenAI
8.06%
48
Command A 03 2025Cohere
4.23%
49
DeepSeek V3p2 ThinkingFireworks
2.35%
50
Jamba Large 1.7AI21 Labs
0.37%
51
DeepSeek V3p2Fireworks
0.00%

The published Finance Agent v1.1 snapshot places Claude Opus 4.7 first at 64.37%. The third row is 3.78 points behind. The broader top-10 range is 6.72 points, so many of the published results sit in a relatively narrow band.

51 models have been evaluated on Finance Agent v1.1. The benchmark falls in the External benchmark mirrors category. We keep external benchmark mirrors separate from the weighted global scoring system, so these results remain source-specific evidence. Finance Agent v1.1 is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About Finance Agent v1.1

Year

2026

Tasks

Financial retrieval, reasoning, modeling, and market-analysis tasks

Format

Accuracy score

Difficulty

Professional financial analyst workflows

BenchLM mirrors the archived Vals Finance Agent v1.1 leaderboard as display-only external evidence. Its private task set and agent configurations remain outside weighted rankings.

Finance Agent v1.1Public benchmark source

BenchLM freshness & provenance

Version

Finance Agent v1.1 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 v1.1 measure?

Evaluates agents on core financial analyst tasks spanning retrieval, numerical reasoning, modeling, and market analysis.

Which model leads the published Finance Agent v1.1 snapshot?

Claude Opus 4.7 currently leads the published Finance Agent v1.1 snapshot with 64.37% finance agent v1.1 score. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on Finance Agent v1.1?

51 AI models are included in BenchLM's mirrored Finance Agent v1.1 snapshot, based on the public leaderboard captured on June 4, 2026.

Last updated: June 4, 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.