Skip to content

Latest commit

 

History

116 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 

Repository files navigation

SOTA LLM/VLM Benchmarks Digest

A curated dashboard of the frontier in AI evaluation. Updated Daily — Target 8 Papers/Day.


🗺️ Navigate the Repo

Resource Description
📅 Full Archive Chronological history of every Daily 8 entry
📚 Benchmark Reference Curated stable reference — 200+ benchmarks by domain
🗂️ Survey Index All deep-dive notes organised by topic area
📋 Weekly Digest Rolling weekly summary with industry trust gaps

🚀 Today's Daily 8 (May 13, 2026)

Paper Modality Key Finding Notes arXiv
LongMemEval-V2 LLM 451 questions / 115M-token histories / 5 memory abilities: AgentRunbook-C 72.5% vs. RAG baseline 48.5% — RAG insufficient for environment-specific expertise accumulation 📄 🔗
TokenHD LLM Token-level hallucination detector: 0.6B trained model surpasses QwQ-32B; scales consistently 0.6B→8B; no step segmentation required 📄 🔗
Rollout Cards LLM 0/50 audited agent repos disclose failed runs; reporting rule changes alone shift scores ±20.9 pp and invert frontier model rankings 📄 🔗
Principal Hierarchies LLM 10 frontier models / 7,136 scenarios: models adhere to professional standards in advisory contexts but abandon them during task execution; reasoning traces suppress recognised knowledge under authority pressure 📄 🔗
MedHopQA LLM BioCreative IX: 10,000 questions (1K scored/9K withheld); disease-centered 2-article multi-hop synthesis; open-ended format blocks answer-elimination shortcut 📄 🔗
MedMemoryBench LLM ~2,000 sessions / ~16,000 turns: memory saturation is universal — all mainstream architectures degrade as clinical information accumulates; complex medical reasoning and noise resilience are fundamental gaps 📄 🔗
ATC Safety Eval LLM Peak Risk Score 0.69 for best model; most LLMs score <0.6 despite high macro-F1 — aggregate accuracy hides unsafe error concentration in high-consequence entity categories 📄 🔗
Rubric RL Hacking LLM Rubric-based RL reward hacking: weak verifiers yield large proxy gains that don't transfer; exploitation grows over training; self-internalization gap detects it without holdout verifiers 📄 🔗

📋 See the full weekly digest →  |  📅 Full archive →


📑 Frontier Model Technical Reports

Model Lab Key Result Notes Link
Claude Opus 4.8 Anthropic 69.2% SWE-Bench Pro / 57.9% HLE (tools) / 83.4% OSWorld-Verified / 1890 GDPval-AA / 84% Online-Mind2Web / first >10% Legal Agent all-pass / $5/$25 per M tokens 📄 🔗
Kimi-K2.6 Moonshot AI 54.0 HLE-Full (beats GPT-5.4) / 58.6 SWE-Bench Pro (best open-weight) / 96.4 AIME 2026 / 1T MoE / Mod. MIT 📄 🔗
Mistral Medium 3.5 Mistral AI 77.6% SWE-Bench Verified / 91.4% τ³-Telecom / 128B dense / replaces 3 prior models / per-request reasoning 📄 🔗
Qwen3.6-27B Alibaba 77.2% SWE-Bench Verified at 27B / 94.1 AIME 2026 / 70.3% AndroidWorld / 1M-token context / Apache-2.0 📄 🔗
GPT-5.4 OpenAI 75.0% OSWorld-V 📄 🔗
GPT-5.4 mini/nano OpenAI OSWorld-mini efficiency leader 📄 🔗
Gemini 3.1 Pro Google 77.1% ARC-AGI-2 📄 🔗
Phi-4 Reasoning Microsoft 15B model, strong MathVista 📄 🔗
DeepSeek-V4-Pro DeepSeek 93.5 LiveCodeBench / 80.6% SWE-Verified / 1M-token context at 27% V3.2 FLOPs / MIT licence 📄 🔗
DeepSeek-V3.2 DeepSeek RL-based logic, MMLU-Pro + IMO 📄 🔗
ARC-AGI-2 ARC Prize Non-semantic visual abduction 📄 🔗
ERNIE 5.0 Baidu Trillion-param unified MoE 📄 🔗
Emu3.5 BAAI 94.03 TIIF-Bench; 20× gen speedup 📄 🔗
Qwen3.5-Omni Alibaba WER 1.11 Librispeech; 119 languages 📄 🔗

🏭 Enterprise Evaluation Roadmap

A prioritised checklist of benchmarks to run against enterprise LLM/VLM deployments — ordered by deployment risk and evaluation ROI.

🔴 Pre-Deployment Gates (Run Before Any Production Release)

  • SimpleQA — hallucination stress-test on every checkpoint before release
  • HalluLens — extrinsic + intrinsic hallucination suites for any RAG or factual output pipeline
  • TraceSafe-Bench — mid-trajectory tool-calling safety before any agentic deployment
  • HINTBench — intrinsic agent safety validation on long agentic trajectories
  • MemEvoBench — memory safety degradation check before persistent agent deployment
  • MedSkillAudit — pre-release skill audit gate (target: <57% below threshold)

🟡 Capability Baselines (Establish Before Fine-Tuning)

  • MMLU-Pro — multi-domain knowledge baseline across 14 disciplines
  • AgentBench — agent capability baseline before and after every major architecture upgrade
  • SWE-bench Verified — code engineering capability baseline
  • StructEval — structured output reliability across 18 formats
  • MIRROR — metacognitive calibration; measure Compositional Calibration Error before deployment
  • SOB — structured extraction accuracy on text/image/audio before any data pipeline deployment
  • KWBench — unprompted problem recognition in professional knowledge work

🟢 Domain-Specific Evaluations (Before Vertical Deployments)

  • MATHVERSE Vision-Only — confirm genuine diagram reading vs. text shortcuts before engineering schematics deployment
  • VLM-RobustBench — geometric robustness before any factory-floor visual deployment
  • TPS-CalcBench — engineering calculation accuracy before safety-critical design tasks
  • IndicDB / Semantic Layers Bench — text-to-SQL accuracy; build semantic layer before deployment
  • AutomationBench — cross-app workflow orchestration; expect <10% without specialised training
  • GTA-2 — multi-step tool workflow completion; expect <15% for complex workflows
  • LongSumEval — QA-based summarisation fidelity before document summarisation deployment
  • Cyber Defense Benchmark — threat-hunting recall before any SOC/security assistant deployment
  • MuDABench — multi-document analytical QA before enterprise knowledge base deployment
  • AgentSearchBench — agent discovery accuracy before routing layer deployment in multi-agent systems

Built with ❤️ for the AI evaluation community. Contributions welcome — see ARCHIVE.md for the full history.

About

A comprehensive repository tracking SOTA LLM/VLM benchmarks, datasets, and evaluation metrics. Features a running digest of research papers and system roadmaps.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors