Vals Index
Updated 12/12/2025
Vals Index
Benchmark consisting of a weighted performance across finance, law and coding tasks. Showing the potential impact that LLM's can have on the economy.
Top Model:
GPT 5.2
Number of models tested
28
Updated 12/11/2025
NewVals Multimodal Index
Benchmark consisting of a weighted performance across finance, law, coding, and education tasks. Showing the potential impact that LLM's can have on the economy.
Top Model:
GPT 5.2
Number of models tested
17
Legal Benchmarks
Updated 12/11/2025
CaseLaw (v2)
Private question-answer benchmark over Canadian court-cases.
Top Model:
GPT 5 Mini
Number of models tested
56
Updated 12/11/2025
LegalBench
Evaluating language models on a wide range of open source legal reasoning tasks.
Top Model:
Gemini 3 Pro (11/25)
Number of models tested
99
Finance Benchmarks
Updated 12/11/2025
CorpFin (v2)
A private benchmark evaluating understanding of long-context credit agreements
Top Model:
Grok 4 Fast (Reasoning)
Number of models tested
79
Updated 12/11/2025
Finance Agent
Evaluating agents on core financial analyst tasks
Top Model:
GPT 5.1
Number of models tested
54
Updated 12/11/2025
MortgageTax
Evaluating reading and understanding tax certificates as images
Top Model:
Gemini 3 Pro (11/25)
Number of models tested
55
Updated 12/11/2025
TaxEval (v2)
A Vals-created set of questions and responses to tax questions
Top Model:
Grok 3
Number of models tested
85
Healthcare Benchmarks
Updated 12/11/2025
MedQA
Evaluating language model bias in medical questions.
Top Model:
o1
Number of models tested
83
Math Benchmarks
Updated 12/11/2025
AIME
Challenging national math exam given to top high-school students
Top Model:
GPT 5.2
Number of models tested
75
Updated 12/7/2025
MATH 500
Academic math benchmark on probability, algebra, and trigonometry
Top Model:
Gemini 3 Pro (11/25)
Number of models tested
59
Updated 12/11/2025
MGSM
A multilingual benchmark for mathematical questions.
Top Model:
Claude Opus 4.5 (Thinking)
Number of models tested
72
Academic Benchmarks
Updated 12/11/2025
GPQA
Graduate-level Google-Proof Q&A benchmark evaluating models on questions that require deep reasoning.
Top Model:
GPT 5.2
Number of models tested
76
Updated 12/11/2025
MMLU Pro
Academic multiple-choice benchmark covering 14 subjects including STEM, humanities, and social sciences.
Top Model:
Gemini 3 Pro (11/25)
Number of models tested
77
Updated 12/7/2025
MMMU
Multimodal Multi-task Benchmark
Top Model:
Gemini 3 Pro (11/25)
Number of models tested
53
Education Benchmarks
Updated 12/11/2025
SAGE
Student Assessment with Generative Evaluation
Top Model:
Claude Opus 4.5 (Thinking)
Number of models tested
35
Coding Benchmarks
Updated 12/12/2025
SWE-bench
Solving production software engineering tasks
Top Model:
GPT 5.2
Number of models tested
40
Updated 12/11/2025
IOI
International Olympiad in Informatics
Top Model:
GPT 5.2
Number of models tested
37
Updated 12/11/2025
LiveCodeBench
Our Implementation of the LiveCodeBench benchmark
Top Model:
GPT 5 Mini
Number of models tested
81
Updated 12/12/2025
Terminal-Bench
State-of-the-art set of difficult terminal-based tasks
Top Model:
GPT 5.2
Number of models tested
42
Updated 12/11/2025
NEWVibe Code Bench
Can models build web applications from scratch?
Top Model:
GPT 5.2
Number of models tested
15