# Who Verifies the Benchmark? Decentralizing Trust in Large Language Model Evaluation

arXiv: https://arxiv.org/abs/2608.07762 · HTML: https://mlsanity.com/paper/2608.07762/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 22 references that are in the map.
- First posted on arXiv 7 Aug 2026.

## Builds on (most cited first, 13 of 13)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI](https://mlsanity.com/paper/2411.04872/) (2024)
- [Large Language Models Reflect the Ideology of their Creators](https://mlsanity.com/paper/2410.18417/) (2024)
- [zkLLM: Zero Knowledge Proofs for Large Language Models](https://mlsanity.com/paper/2404.16109/) (2024)
- [Play Favorites: A Statistical Method to Measure Self-Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2508.06709/) (2025)
- [BiasScope: Towards Automated Detection of Bias in LLM-as-a-Judge Evaluation](https://mlsanity.com/paper/2602.09383/) (2026)
- [Beyond Partisan Leaning: A Comparative Analysis of Political Bias in Large Language Models](https://mlsanity.com/paper/2412.16746/) (2024)
- [Uncovering Political Bias in Large Language Models using Parliamentary Voting Records](https://mlsanity.com/paper/2601.08785/) (2026)
- [Quantifying Cognitive Bias Induction in LLM-Generated Content](https://mlsanity.com/paper/2507.03194/) (2025)
- [InfiCoEvalChain: A Blockchain-Based Decentralized Framework for Collaborative LLM Evaluation](https://mlsanity.com/paper/2602.08229/) (2026)
- [Counterfactual LLM-based Framework for Measuring Rhetorical Style](https://mlsanity.com/paper/2512.19908/) (2025)

## Abstract (arXiv)

LLM benchmarks can build an organization's reputation and attract customers, but only when results are transparent and verifiable. Unverified claims that DeepSeek R1 outperformed OpenAI's o1 contributed to market panic on January 27, 2025, when Nvidia lost USD589 billion in market value. Yet vendor benchmarks often depend on an honor system. Academic reassessments and independent leaderboards have found undisclosed changes to proprietary models, contaminated training data, and selective reporting. LLM-as-a-judge methods scale evaluation by reducing human review. Studies, however, suggest that judges may show identity-aware bias, scoring an answer according to its source model rather than its quality. This bias has not been fully measured or corrected across politically sensitive, reasoning-intensive, and preference-based tasks. We examine this problem using seven verifier models: GPT-OSS 120B, Llama 3.3 70B, GLM 5.1, Qwen3 32B, DeepSeek V4 Pro, Mistral Large3, and Sarvam M. They score anonymous and identity-disclosed responses from three primary models on 58 factual, reasoning, political, and preference-based questions. Identity disclosure slightly raises scores for factual questions, moderately affects stress-reasoning tasks, and causes large changes for geopolitically sensitive topics. Notable results include GLM5.1 (+7.00 points, p = 0.0249) and Llama 3.3 70B (+1.56 points, p = 0.00). We also introduce a blockchain-based commit-reveal protocol using Autonomous Economic Agents on an Ethereum-compatible ledger. In Phase 1, each judge records a one-way hash of its score and a secret salt before candidate identities are revealed. In Phase 2, the identity and raw score are disclosed and verified on-chain. This creates a tamper-evident audit trail that separates blind evaluation from post-hoc claims and reduces the verification burden on independent researchers and leaderboard operators.