Weekly benchmark review: 2026-06-15

[github-actions]

Weekly benchmark review (2026-06-15)

Automated check from scripts/weekly-benchmarks-check.mjs. Triage and either:

• Update data/benchmarks.json if a new flagship model dropped this week, then close this issue, OR
• Comment noop and close if nothing actionable surfaced.

Current state of data/benchmarks.json

• lastUpdated: 2026-06-11 (4 days ago)

• Models tracked: 20

• Benchmarks tracked: 5

• Models released within last 60 days: 2

  • 2026-06 | Anthropic | Claude Fable 5
  • 2026-05 | Anthropic | Claude Opus 4.8

Model-release-flavored news, last 7 days

Matched 10 articles (keyword scan; not all will be real releases).

Date	Source	Title
2026-06-15	Hacker News AI	Show HN: Spotlight shows what your Claude Code/Codex are doing
2026-06-15	Hacker News AI	Claude Corps
2026-06-15	Google AI Blog	We’re strengthening our presence in Alabama through new investments and community support.
2026-06-15	ZDNet AI	Google Maps vs. Waze: I've driven 100+ miles with the two best navigation apps - this one's better
2026-06-15	arXiv cs.AI	WorkBench Revisited: Workplace Agents Two Years On
2026-06-15	arXiv cs.AI	YeasierAgent: Agentic Social Sandbox as a Canvas for Intent-Driven Creation of Platform-Agnostic Symbiotic Agent-Native Applications
2026-06-13	The Verge AI	My yard is dying, so I made an app for that
2026-06-13	WIRED AI	Anthropic Says It’s Taking Claude Fable 5 Offline to Comply With US Government Order
2026-06-10	NVIDIA AI Blog	NVIDIA Accelerates Google DeepMind’s DiffusionGemma for Local AI
2026-06-09	NVIDIA AI Blog	NVIDIA Confidential Computing to Help Expand Apple’s Private Cloud Compute

Sources: Hacker News AI (2), arXiv cs.AI (2), NVIDIA AI Blog (2), Google AI Blog (1), ZDNet AI (1), The Verge AI (1), WIRED AI (1)

HF Open LLM Leaderboard top 10

Captured: 2026-06-15

Rank	Model
1	MaziyarPanahi_calme-3.2-instruct-78b_bfloat16 (avg 52.08 · 78B)
2	MaziyarPanahi_calme-3.1-instruct-78b_bfloat16 (avg 51.29 · 78B)
3	dfurman_CalmeRys-78B-Orpo-v0.1_bfloat16 (avg 51.23 · 78B)
4	MaziyarPanahi_calme-2.4-rys-78b_bfloat16 (avg 50.77 · 78B)
5	huihui-ai_Qwen2.5-72B-Instruct-abliterated_bfloat16 (avg 48.11 · 73B)
6	Qwen_Qwen2.5-72B-Instruct_bfloat16 (avg 47.98 · 73B)
7	MaziyarPanahi_calme-2.1-qwen2.5-72b_bfloat16 (avg 47.86 · 73B)
8	newsbang_Homer-v1.0-Qwen2.5-72B_bfloat16 (avg 47.46 · 73B)
9	ehristoforu_qwen2.5-test-32b-it_bfloat16 (avg 47.37 · 33B)
10	Saxo_Linkbricks-Horizon-AI-Avengers-V1-32B_bfloat16 (avg 47.34 · 33B)

---

What "needs update" usually means

1. A flagship from Anthropic / OpenAI / Google / Meta / Mistral / DeepSeek / xAI launched this week → add a row to data/benchmarks.json.
2. A tracked model has materially-shifted benchmark scores (re-running, methodology change) → update the row.
3. A new benchmark itself (e.g. a successor to MMLU-Pro) is becoming canonical → add it.

What it usually does NOT mean

• Research papers about benchmarks (those land on /research, not /benchmarks).
• HN opinion threads about a model.
• Pricing-only changes (those go in data/pricing.json).

Bump lastUpdated in data/benchmarks.json whenever you change anything else in the file.