Financial Coaching Bench
Models interview a simulated client about a household financial problem and propose a plan.
The judge checks the plan against practitioner criteria across 256 scored scenarios.
- Made by
- Vals AI
- Released
- November 2026
- Kind
- Finance
- Level
- Expert
- Scored
- Graded by a model
- Answers
- Agent task
- Tasks
- Kept private
- Measures
- Capability
- Subject
- Economics and business
- Language
- English
- Interaction
- Multi-turn
- Items from
- Generated
- Refresh
- One fixed set
- Run by
- A host
- Occupations
- Business and financial operations
- In views
- Law and finance
- Strongest model tested
- GPT-6 Astra #4 on the capability index
- Last model added
- October 2026
- Scores refreshed
- November 20th, 2026
Claude Opus 5.5 leads with 76.2%
Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart.
- 76.2 Claude Opus 5.5
- 75.7
Muse Spark 1.2
- 75.7 Claude Fable 5.1
- 75.6
Qwen 3.8 Max
- 75.4 MiMo-V2.6 Pro
- 75.0
Muse Wonder Full
- 74.9 Claude Sonnet 5.5
- 74.9 GPT-5.6 Sol
- 74.5 Kimi K3
- 74.1 Grok 4.7
- 74.1 GLM-5.3
- 73.8
Muse Wonder
- 73.1
Gemini 4 Argon
- 72.8
DeepSeek V4.1 Flash
- 71.0
Muse Spark 1.3
- 71.0 GPT-5.6 Terra
- 69.3 GPT-5.6 Luna
- 69.0
MiniMax-M3
- 68.5 GPT-6.1 Sol
- 67.5 GPT-6 Astra
- 66.7
Gemini 3.1 Pro
- 66.3
Gemini 3.8 Flash
- 65.8
Gemini 3.6 Flash
- 65.2 GPT-6 Luna
- 63.0
Gemini 3.5 Flash
- 62.6 GPT-6 Sol
- 57.5
Gemini 3.5 Flash-Lite
- 1 Claude Opus 5.5 76.2%
- 2
Muse Spark 1.2 75.7%
- 3 Claude Fable 5.1 75.7%
- 4
Qwen 3.8 Max 75.6%
- 5 MiMo-V2.6 Pro 75.4%
- 6
Muse Wonder Full 75%
- 7 Claude Sonnet 5.5 74.9%
- 8 GPT-5.6 Sol 74.9%
- 9 Kimi K3 74.5%
- 10 Grok 4.7 74.1%
- 11 GLM-5.3 74.1%
- 12
Muse Wonder 73.8%
- 13
Gemini 4 Argon 73.1%
- 14
DeepSeek V4.1 Flash 72.8%
- 15
Muse Spark 1.3 71%
- 16 GPT-5.6 Terra 71%
- 17 GPT-5.6 Luna 69.3%
- 18
MiniMax-M3 69%
- 19 GPT-6.1 Sol 68.5%
- 20 GPT-6 Astra 67.5%
- 21
Gemini 3.1 Pro 66.7%
- 22
Gemini 3.8 Flash 66.3%
- 23
Gemini 3.6 Flash 65.8%
- 24 GPT-6 Luna 65.2%
- 25
Gemini 3.5 Flash 63%
- 26 GPT-6 Sol 62.6%
- 27
Gemini 3.5 Flash-Lite 57.5%
Source: Official Financial Coaching Bench leaderboard
| # | Model | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | 76.2% ±3 | Sep 2026 | Official leaderboard | |
| 2 | | 75.7% ±3 | Aug 2026 | Official leaderboard | |
| 3 | Claude Fable 5.1 | 75.7% ±3 | Sep 2026 | Official leaderboard | |
| 4 | | 75.6% ±2.9 | Aug 2026 | Official leaderboard | |
| 5 | MiMo-V2.6 Pro | 75.4% ±2.8 | Sep 2026 | Official leaderboard | |
| 6 | | 75% ±3.1 | Oct 2026 | Official leaderboard | |
| 7 | Claude Sonnet 5.5 | 74.9% ±3 | Sep 2026 | Official leaderboard | |
| 8 | GPT-5.6 Sol | 74.9% ±3 | Jul 2026 | Official leaderboard | |
| 9 | Kimi K3 | 74.5% ±2.9 | Jul 2026 | Official leaderboard | |
| 10 | Grok 4.7 | 74.1% ±3 | Sep 2026 | Official leaderboard | |
| 11 | GLM-5.3 | 74.1% ±2.9 | Aug 2026 | Official leaderboard | |
| 12 | | 73.8% ±3 | Oct 2026 | Official leaderboard | |
| 13 | | 73.1% ±2.9 | Sep 2026 | Official leaderboard | |
| 14 | | 72.8% ±3.1 | Sep 2026 | Official leaderboard | |
| 15 | | 71% ±3 | Sep 2026 | Official leaderboard | |
| 16 | GPT-5.6 Terra | 71% ±3 | Jul 2026 | Official leaderboard | |
| 17 | GPT-5.6 Luna | 69.3% ±3.2 | Jul 2026 | Official leaderboard | |
| 18 | | 69% ±3.1 | Jun 2026 | Official leaderboard | |
| 19 | GPT-6.1 Sol | 68.5% ±3.1 | Sep 2026 | Official leaderboard | |
| 20 | GPT-6 Astra | 67.5% ±3.3 | Sep 2026 | Official leaderboard | |
| 21 | | 66.7% ±2.9 | Feb 2026 | Official leaderboard | |
| 22 | | 66.3% ±3.1 | Sep 2026 | Official leaderboard | |
| 23 | | 65.8% ±3.1 | Jul 2026 | Official leaderboard | |
| 24 | GPT-6 Luna | 65.2% ±3.3 | Sep 2026 | Official leaderboard | |
| 25 | | 63% ±3.2 | May 2026 | Official leaderboard | |
| 26 | GPT-6 Sol | 62.6% ±3.4 | Sep 2026 | Official leaderboard | |
| 27 | | 57.5% ±3.3 | Jul 2026 | Official leaderboard |
The best score, 76.2%, costs $1.63 a task
Runs on the cost frontier score higher than any run that's cheaper. MiMo-V2.6 Pro comes within 0.8 points of the best for $0.01 a task, 163 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official Financial Coaching Bench leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Opus 5.5 | 76.2% | $1.63 | |||
| 75.7% | $0.06 | ||||
| Claude Fable 5.1 | 75.7% | $1.14 | |||
| 75.6% | $0.13 | ||||
| MiMo-V2.6 Pro | 75.4% | $0.01 | |||
| 75% | $0.44 | ||||
| Claude Sonnet 5.5 | 74.9% | $0.80 | |||
| GPT-5.6 Sol | 74.9% | $0.47 | |||
| Kimi K3 | 74.5% | $0.19 | |||
| Grok 4.7 | 74.1% | $0.24 | |||
| GLM-5.3 | 74.1% | $0.09 | |||
| 73.8% | $0.32 | ||||
| 73.1% | $0.16 | ||||
| 72.8% | $0.02 | ||||
| 71% | $0.07 | ||||
| GPT-5.6 Terra | 71% | $0.31 | |||
| max | 70.3% | $0.09 | |||
| GPT-5.6 Luna | 69.3% | $0.02 | |||
| 69% | $0.03 | ||||
| GPT-6.1 Sol | 68.5% | $0.30 | |||
| GPT-6 Astra | 67.5% | $1.72 | |||
| 66.7% | $0.12 | ||||
| 66.3% | $0.10 | ||||
| 65.8% | $0.10 | ||||
| GPT-6 Luna | 65.2% | $0.02 | |||
| 63% | $0.13 | ||||
| GPT-6 Sol | 62.6% | $0.23 | |||
| 57.5% | $0.03 |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Financial Coaching Bench leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Financial Coaching Bench leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Law, finance and medicine
- MedXpertQA-MM In use Models answer expert-level medical exam questions that combine images with clinical records and test results. Scoring is accuracy.
Qwen 3.8 Max 80.4%
- HealthBench Professional In use 525 physician-authored tasks from real clinician chats (care consult, documentation, research) with physician-adjudicated rubrics. Claude Sonnet 5.5 69.2%
- HealthBench In use 5,000 realistic health conversations graded against physician-written rubrics. A length-adjusted variant penalizes verbosity. GPT-5 67.2%
- FinSearchComp In use Agents search the web to fetch live financial data, look up history, and run multi-step investigations, across 635 expert-written questions. Scored by answer accuracy.
Ling-3.1-flash 81.7%
- KorMedMCQA In use Models answer 7,469 multiple-choice questions from Korean licensing exams for doctors, nurses, pharmacists and dentists, held from 2012 to 2024. o1-preview 92.7%
- Harvey LAB-AA v1.1 In use Artificial Analysis's run of Harvey's Legal Agent Benchmark on Harvey's newer private set of 120 tasks across 24 practice areas. A deliverable with a material hallucination scores zero, and the headline is the share of judges who find every rubric criterion passed. GPT-6.2 Astra 15%
Data audit
All 11 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access The tasks are private.
- Pass Confidence Checked against a primary source.
Scores 5 pass
- Pass Independent runs Scores from the official leaderboard (27 entries).
- Pass Models scored 27 models we track.
- Pass Newest score The newest is from October 2026, for Muse Wonder.
- Pass Frontier models 6 of the top 10 have a score, led by GPT-6 Astra (#4).
- Pass Headroom The best is 76.2%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on vals.ai: 28 rows for models we track at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.