BenchLeader

Financial Coaching Bench leaderboard

As of 16 Nov 2026, the top score on Financial Coaching Bench is 76.2% by Claude Opus 5.5 (Anthropic), ahead of Muse Spark 1.2 at 75.7%, across 28 model configurations with a published result (Vals AI, result dated 13 Nov 2026). Coaching a household through a real financial problem. Run by Vals AI. Financial Coaching Bench is shown for reference only and does not count toward the BenchLeader Index.

Key facts (as of 16 Nov 2026)

  • Claude Opus 5.5 holds the top Financial Coaching Bench score at 76.2% (Vals AI, 13 Nov 2026).
  • Muse Spark 1.2 is second on Financial Coaching Bench at 75.7% (Vals AI, 13 Nov 2026).
  • Financial Coaching Bench: Coaching a household through a real financial problem. Run by Vals AI (Vals AI).
  • 28 model configurations have a published Financial Coaching Bench result on BenchLeader (BenchLeader, 16 Nov 2026).
  • Financial Coaching Bench does not feed the BenchLeader Index; it is shown for reference (BenchLeader methodology).

Coaching a household through a real financial problem. Run by Vals AI.

Published by
Vals AI
Category
Knowledge
Index weight
Reference only
Models
28
Data as of
16 Nov 2026

Vals AI (vals.ai).

28 of 28
#
1Claude Opus 5.5max76.2%68.4$1.632026-11-13
2Muse Spark 1.2xhigh75.7%61.5$0.0592026-11-13
3Claude Fable 5.1max75.7%66.7$1.142026-11-13
4Qwen3.8 Maxmax75.6%58.7$0.1282026-11-13
5MiMo-V2.6-Pro75.4%57.5$0.0132026-11-13
6Muse Wonder Fullmax75.0%61.7$0.4442026-11-13
7Claude Sonnet 5.5max74.9%64.2$0.8032026-11-13
8GPT-5.6 Solmax74.9%65.3$0.4702026-11-13
9Kimi K3max74.5%60.2$0.1912026-11-13
10Grok 4.7xhigh74.1%57.4$0.2372026-11-13
11GLM 5.3max74.1%58.8$0.0942026-11-13
12Muse Wondermax73.8%60.8$0.3212026-11-13
13Gemini 4 Argonhigh73.1%65.3$0.1552026-11-13
14DeepSeek V4.1 Flashhigh72.8%55.6$0.0152026-11-13
15Muse Spark 1.3xhigh71.0%58.1$0.0702026-11-13
16GPT-5.6 Terramax71.0%59.5$0.3082026-11-13
17Muse Spark 1.3max70.3%60.6$0.0862026-11-13
18GPT-5.6 Lunamax69.3%56.2$0.0232026-11-13
19MiniMax M369.0%56.1$0.0272026-11-13
20GPT-6.1 Solmax68.5%66.6$0.2952026-11-13
21GPT-6 Astramax67.5%67.3$1.722026-11-13
22Gemini 3.1 Prohigh66.7%60.4$0.1222026-11-13
23Gemini 3.8 Flashhigh66.3%59.4$0.1002026-11-13
24Gemini 3.6 Flashhigh65.8%61.0$0.1012026-11-13
25GPT-6 Lunamax65.2%55.1$0.0212026-11-13
26Gemini 3.5 Flashhigh63.0%62.5$0.1292026-11-13
27GPT-6 Solmax62.6%62.6$0.2332026-11-13
28Gemini 3.5 Flash Litehigh57.5%47.8$0.0262026-11-13

More knowledge benchmarks · All LLM benchmarks

Cite as: BenchLeader, “Financial Coaching Bench leaderboard”, data as of 16 Nov 2026, https://www.benchleader.com/benchmarks/vals_financial_coaching.

Financial Coaching Bench: questions

What does Financial Coaching Bench measure?
Coaching a household through a real financial problem. Run by Vals AI. Scores are reported in percent of tasks solved; higher is better.
What is the top score on Financial Coaching Bench?
As of 16 Nov 2026, the highest score on Financial Coaching Bench is 76.2% by Claude Opus 5.5 (result dated 13 Nov 2026), ahead of Muse Spark 1.2 at 75.7%. Scores come from Vals AI and are re-read daily.
Which AI model leads Financial Coaching Bench?
Claude Opus 5.5 leads Financial Coaching Bench with 76.2% as of 16 Nov 2026 (result dated 13 Nov 2026), ahead of Muse Spark 1.2 at 75.7%.
How many models have Financial Coaching Bench results?
28 model configurations have a Financial Coaching Bench result on BenchLeader, all taken from Vals AI.
Who runs Financial Coaching Bench and how often is it updated?
Financial Coaching Bench is published by Vals AI. BenchLeader re-reads the published results once a day and records the date each result was published.
Does Financial Coaching Bench count toward the BenchLeader Index?
No. Financial Coaching Bench is shown for reference but left out of the composite index.