# www.vals.ai

> AI-optimized mirror of www.vals.ai containing 47 pages totalling 19,350 words of clean markdown content, structured data, and semantic HTML. Original source: https://www.vals.ai/. Last updated: 2026-04-17T00:50:27.906Z.

Each page is available as HTML (with JSON-LD structured data) and Markdown (text-only, ideal for LLMs and RAG).

## Homepage

- [Home](/site-root.html): Independent Evaluation, Unbiased Benchmarks (1,218 words)

## Articles & Blog Posts

- [Gemini 3 Flash (12/25)](/models/google_gemini-3-flash-preview/index.html): All CompaniesRelease date (218 words)
- [GPT 5.2](/models/openai_gpt-5-2-2025-12-11.html): All CompaniesRelease date (216 words)
- [GPT 5](/models/openai_gpt-5-2025-08-07/index.html): All CompaniesRelease date (212 words)
- [MMLU Pro](/benchmarks/mmlu_pro/index.html): Academic (1,220 words)
- [Claude Opus 4.6 (Thinking)](/models/anthropic_claude-opus-4-6-thinking/index.html): All CompaniesRelease date (218 words)
- [GPT 5.1](/models/openai_gpt-5-1-2025-11-13.html): All CompaniesRelease date (210 words)
- [Claude Sonnet 4.5 (Thinking)](/models/anthropic_claude-sonnet-4-5-20250929-thinking/index.html): All CompaniesRelease date (213 words)
- [GLM 4.7](/models/zai_glm-4-7.html): All CompaniesRelease date (206 words)
- [Mistral Large 3](/models/mistralai_mistral-large-2512/index.html): All CompaniesRelease date (212 words)
- [Command A](/models/cohere_command-a-03-2025/index.html): All CompaniesRelease date (190 words)
- [AIME](/benchmarks/aime/index.html): Math (512 words)
- [CorpFin (v2)](/benchmarks/corp_fin_v2/index.html): Finance (980 words)
- [GLM 5.1](/models/zai_glm-5-1-thinking.html): All CompaniesRelease date (205 words)
- [Muse Spark](/models/meta_muse_spark/index.html): All CompaniesRelease date (197 words)
- [Vals Multimodal Index](/benchmarks/vals_multimodal_index/index.html): Index (670 words)
- [Vals Index](/benchmarks/vals_index/index.html): Index (643 words)
- [GLM 5](/models/zai_glm-5-thinking/index.html): All CompaniesRelease date (203 words)
- [MortgageTax](/benchmarks/mortgage_tax/index.html): Finance (914 words)
- [Grok 4.20 (Reasoning)](/models/grok_grok-4-20-0309-reasoning.html): All CompaniesRelease date (214 words)
- [MiniMax-M2.1](/models/minimax_minimax-m2-1.html): All CompaniesRelease date (201 words)
- [Grok 4](/models/grok_grok-4-0709/index.html): All CompaniesRelease date (208 words)
- [Kimi K2 Thinking](/models/kimi_kimi-k2-thinking/index.html): All CompaniesRelease date (200 words)
- [MiniMax-M2.5](/models/minimax_minimax-m2-5-lightning.html): All CompaniesRelease date (199 words)
- [GPT OSS 120B](/models/fireworks_gpt-oss-120b/index.html): All CompaniesRelease date (198 words)
- [Qwen 3.5 Plus](/models/alibaba_qwen3-5-plus-thinking.html): All CompaniesRelease date (210 words)
- [Gemini 2.5 Pro](/models/google_gemini-2-5-pro.html): All CompaniesRelease date (191 words)
- [MedCode](/benchmarks/medcode/index.html): Healthcare (978 words)
- [Trinity Large Thinking](/models/arcee-ai_trinity-large-thinking/index.html): All CompaniesRelease date (177 words)
- [MiniMax-M2.7](/models/minimax_minimax-m2-7.html): All CompaniesRelease date (204 words)
- [DeepSeek V3.2 (Thinking)](/models/fireworks_deepseek-v3p2-thinking/index.html): All CompaniesRelease date (207 words)
- [Terminal-Bench 2.0](/benchmarks/terminal-bench-2/index.html): Coding (543 words)
- [CaseLaw (v2)](/benchmarks/case_law_v2/index.html): Legal (765 words)
- [TaxEval (v2)](/benchmarks/tax_eval_v2/index.html): Finance (821 words)
- [Qwen 3.6 Plus](/models/alibaba_qwen3-6-plus.html): All CompaniesRelease date (207 words)
- [GPT 5.4](/models/openai_gpt-5-4-2026-03-05.html): All CompaniesRelease date (216 words)
- [Gemini 3.1 Pro Preview (02/26)](/models/google_gemini-3-1-pro-preview.html): All CompaniesRelease date (219 words)
- [Claude Opus 4.7](/models/anthropic_claude-opus-4-7/index.html): All CompaniesRelease date (212 words)
- [Kimi K2.5](/models/kimi_kimi-k2-5-thinking.html): All CompaniesRelease date (213 words)
- [MMMU Pro](/benchmarks/mmmu/index.html): Academic (579 words)
- [Gemini 3 Pro (11/25)](/models/google_gemini-3-pro-preview/index.html): All CompaniesRelease date (215 words)
- [Claude Opus 4.5 (Thinking)](/models/anthropic_claude-opus-4-5-20251101-thinking/index.html): All CompaniesRelease date (215 words)
- [Claude Sonnet 4.6](/models/anthropic_claude-sonnet-4-6/index.html): All CompaniesRelease date (214 words)
- [Gemma 4 31B IT](/models/google_gemma-4-31b-it/index.html): All CompaniesRelease date (191 words)
- [GPQA](/benchmarks/gpqa/index.html): Academic (1,511 words)
- [SWE-bench](/benchmarks/swebench/index.html): Coding (903 words)
- [Application Reports](/application-reports/alexi/index.html): Comprehensive legal technology platform providing advanced research, document analysis, and case management solutions for legal professionals (482 words)

## Resources

- [Full Page Index](/index.html): Browse all cached pages with rich metadata
- [About This Cache](/content/about.html): Methodology, technical details, and usage guidelines
- [XML Sitemap](/content/sitemap.xml): Machine-readable sitemap for crawler discovery
- [Robots.txt](/content/robots.txt): Crawler directives