BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases7

Finance Agent v2 leaderboard

As of 6 Nov 2026, the top score on Finance Agent v2 is 65.4% by Gemini 4 Argon (Google), ahead of Gemini 3.8 Flash at 61.4%, across 79 model configurations with a published result (Vals AI, result dated 29 Oct 2026). Tasks a junior financial analyst does: pulling figures from filings, computing ratios, reconciling numbers, with tools available. Finance Agent v2 is shown for reference only and does not count toward the BenchLeader Index.

Key facts (as of 6 Nov 2026)

  • Gemini 4 Argon holds the top Finance Agent v2 score at 65.4% (Vals AI, 29 Oct 2026).
  • Gemini 3.8 Flash is second on Finance Agent v2 at 61.4% (Vals AI, 29 Oct 2026).
  • Finance Agent v2: Core financial-analyst tasks with tools. Run by Vals AI (Vals AI).
  • 79 model configurations have a published Finance Agent v2 result on BenchLeader (BenchLeader, 6 Nov 2026).
  • Finance Agent v2 does not feed the BenchLeader Index; it is shown for reference (BenchLeader methodology).

Core financial-analyst tasks with tools. Run by Vals AI.

Published by
Vals AI
Category
Agents & tools
Index weight
Reference only
Models
79
Data as of
6 Nov 2026

Vals AI (vals.ai).

What the test looks like

Tasks a junior financial analyst does: pulling figures from filings, computing ratios, reconciling numbers, with tools available.

How it is scored

Accuracy across tasks, run by Vals AI.

What to keep in mind

Overlaps with CorpFin; this version is agentic and tool-using.

Top 15
  1. 1Gemini 4 Argon (high)65.4%
  2. 2Gemini 3.8 Flash (high)61.4%
  3. 3Muse Spark Open (xhigh)61.3%
  4. 4Muse Spark 1.2 (xhigh)60.6%
  5. 5Muse Spark 1.3 (max)60.0%
  6. 6Muse Wonder Full (max)59.1%
  7. 7Gemini 3.7 Flash (high)59.0%
  8. 8Muse Spark 1.3 (xhigh)58.9%
  9. 9Claude Fable 5.158.9%
  10. 10Claude Opus 558.6%
  11. 11Claude Opus 5.558.6%
  12. 12Claude Sonnet 5.558.1%
  13. 13Qwen3.8 Max Internal57.9%
  14. 14Gemini 3.5 Flash (high)57.9%
  15. 15GLM 5.3 Flash (max)57.9%
79 of 79
#
1Gemini 4 Argonhigh65.4%66.0$4.382026-10-29
2Gemini 3.8 Flashhigh61.4%62.0$2.002026-10-29
3Muse Spark Openxhigh61.3%54.0$0.7712026-10-29
4Muse Spark 1.2xhigh60.6%61.7$0.7702026-10-29
5Muse Spark 1.3max60.0%62.0$0.7572026-10-29
6Muse Wonder Fullmax59.1%62.9$2.392026-10-29
7Gemini 3.7 Flashhigh59.0%62.2$1.482026-10-29
8Muse Spark 1.3xhigh58.9%58.5$0.7412026-10-29
9Claude Fable 5.158.9%66.4$8.352026-10-29
10Claude Opus 558.6%65.2$5.122026-10-29
11Claude Opus 5.558.6%63.4$9.222026-10-29
12Claude Sonnet 5.558.1%–$6.552026-10-29
13Qwen3.8 Max Internal57.9%–$3.032026-10-29
14Gemini 3.5 Flashhigh57.9%62.5$2.512026-10-29
15GLM 5.3 Flashmax57.9%54.2$0.0952026-10-29
16MiMo-V2.6-Pro57.3%57.3$0.1992026-10-29
17Muse Spark 1.1xhigh57.2%59.5$0.7232026-10-29
18DeepSeek V4.1 Flash 1017max57.0%59.2$0.4632026-10-29
19Muse Wondermax56.6%62.3$2.672026-10-29
20Claude Fable 556.3%66.5$8.062026-10-29
21Gemini 3.6 Flashhigh56.3%61.2$1.402026-10-29
22MiMo-V2.6-Flash56.3%55.0$0.0722026-10-29
23GLM 5.3max55.8%59.0$1.072026-10-29
24Hy455.1%55.7$0.5902026-10-29
25GPT-5.6 Lunamax55.0%56.3$0.2792026-10-29
26Ling 3.0 Flash Af Rc354.9%–$0.0452026-10-29
27Mistral Large 4high54.7%49.5$0.6152026-10-29
28GPT-5.6 Terramax54.4%60.7$3.632026-10-29
29Claude Haiku 5.554.1%–$1.642026-10-29
30Claude Opus 4.853.9%60.0$4.222026-10-29
31Claude Sonnet 553.9%55.9$0.7512026-10-29
32GPT-5.6 Solmax53.8%65.4$1.252026-10-29
33Grok 4.6high53.7%60.5$1.662026-10-29
34GPT-6 Astramax53.5%67.8$6.822026-10-29
35DeepSeek V4.1 Flashhigh53.5%55.7$0.2072026-10-29
36Kimi K3max53.1%62.1$1.912026-10-29
37Grok 4.7xhigh52.3%58.3$2.722026-10-29
38GPT-6.1 Solmax52.0%67.3$1.622026-10-29
39Ember-151.9%–$1.952026-10-29
40GPT-5.5xhigh51.8%64.3$4.152026-10-29
41Claude Opus 4.751.5%63.1$4.032026-10-29
42Claude Sonnet 4.651.0%58.2$2.412026-10-29
43Step 5 Preview50.7%54.9$0.6192026-10-29
44Qwen3.8 Maxmax50.6%58.8$1.242026-10-29
45DeepSeek V4 Promax50.4%57.0$0.8802026-10-29
46GPT-6 Lunamax49.9%56.7$0.1242026-10-29
47GLM 5.249.7%51.5$0.7142026-10-29
48DeepSeek V4 Flashhigh49.5%57.3$0.2762026-10-29
49GPT-6 Solmax49.0%63.3$2.122026-10-29
50Qwen3.8 27Bxhigh48.5%52.5$0.7492026-10-29
51Grok 4.5high48.4%56.9$1.162026-10-29
52MiniMax M348.3%56.4$0.3232026-10-29
53Qwen3.7max47.8%60.3$0.5532026-10-29
54Gemini 3.5 Flash Litehigh47.4%47.9$0.3902026-10-29
55Inkling46.6%47.5$0.9962026-10-29
56GPT-5.4 Minixhigh45.4%56.0$1.202026-10-29
57Kimi K2.644.9%55.2$1.142026-10-29
58GLM 5.144.8%55.7$0.6182026-10-29
59Gemini 3.1 Prohigh43.0%60.1$1.592026-10-29
60Gemini 3 Flashhigh42.5%58.3$0.5712026-10-29

More agents & tools benchmarks · All LLM benchmarks

Related benchmarks

Top head-to-heads on Finance Agent v2

Cite as: BenchLeader, “Finance Agent v2 leaderboard”, data as of 6 Nov 2026, https://www.benchleader.com/benchmarks/vals_finance_agent.

Finance Agent v2: questions

What does Finance Agent v2 measure?
Tasks a junior financial analyst does: pulling figures from filings, computing ratios, reconciling numbers, with tools available. Scores are reported in percent of tasks solved; higher is better.
What is the top score on Finance Agent v2?
As of 6 Nov 2026, the highest score on Finance Agent v2 is 65.4% by Gemini 4 Argon (result dated 29 Oct 2026), ahead of Gemini 3.8 Flash at 61.4%. Scores come from Vals AI and are re-read daily.
Which AI model leads Finance Agent v2?
Gemini 4 Argon leads Finance Agent v2 with 65.4% as of 6 Nov 2026 (result dated 29 Oct 2026), ahead of Gemini 3.8 Flash at 61.4%.
How many models have Finance Agent v2 results?
79 model configurations have a Finance Agent v2 result on BenchLeader, all taken from Vals AI.
Who runs Finance Agent v2 and how often is it updated?
Finance Agent v2 is published by Vals AI. BenchLeader re-reads the published results once a day and records the date each result was published.
Does Finance Agent v2 count toward the BenchLeader Index?
No. Finance Agent v2 is shown for reference but left out of the composite index.