Models
Each organization appears at its frontier tier as of its elicitation date, and superseded models stay in the panel — so generation-to-generation shifts are directly observable. Tightness is the model's average 90 percent interval-width rank across the 13 canonical quantities (1 = narrowest of 29).
GPT-5.4
- Organization
- OpenAI
- Wave
- April 2026
- Tightness
- #14.2
GPT-5.4 mini
- Organization
- OpenAI
- Wave
- April 2026
- Tightness
- #21.8
GPT-5.4 nano
- Organization
- OpenAI
- Wave
- April 2026
- Tightness
- #17.7
Claude Opus 4.7
- Organization
- Anthropic
- Wave
- April 2026
- Tightness
- #8.8
Claude Sonnet 4.6
- Organization
- Anthropic
- Wave
- April 2026
- Tightness
- #12.8
Claude Haiku 4.5
- Organization
- Anthropic
- Wave
- April 2026
- Tightness
- #8.8
Gemini 3.1 Pro
- Organization
- Wave
- April 2026
- Tightness
- #10.3
Gemini 3 Flash
- Organization
- Wave
- April 2026
- Tightness
- #12.2
Gemini 3.1 Flash-Lite
- Organization
- Wave
- April 2026
- Tightness
- #13.1
Grok 4.20
- Organization
- xAI
- Wave
- April 2026
- Tightness
- #22.3
Grok 4.1 Fast
- Organization
- xAI
- Wave
- April 2026
- Tightness
- #18.0
GPT-5.5
- Organization
- OpenAI
- Wave
- July 2026 frontier
- Tightness
- #14.2
Claude Fable 5
- Organization
- Anthropic
- Wave
- July 2026 frontier
- Tightness
- #6.5
Claude Opus 4.8
- Organization
- Anthropic
- Wave
- July 2026 frontier
- Tightness
- #10.4
Claude Sonnet 5
- Organization
- Anthropic
- Wave
- July 2026 frontier
- Tightness
- #9.2
Gemini 3.5 Flash
- Organization
- Wave
- July 2026 frontier
- Tightness
- #12.5
Grok 4.3
- Organization
- xAI
- Wave
- July 2026 frontier
- Tightness
- #17.5
DeepSeek V4 Pro
- Organization
- DeepSeek
- Wave
- July 2026 independent labs
- Tightness
- #18.8
Qwen 3.7 Max
- Organization
- Alibaba
- Wave
- July 2026 independent labs
- Tightness
- #19.2
Kimi K2.6
- Organization
- Moonshot AI
- Wave
- July 2026 independent labs
- Tightness
- #21.3
GLM-5.2
- Organization
- Zhipu AI
- Wave
- July 2026 independent labs
- Tightness
- #19.5
MiniMax M3
- Organization
- MiniMax
- Wave
- July 2026 independent labs
- Tightness
- #17.6
GPT-5.6 Sol
- Organization
- OpenAI
- Wave
- July 2026 GPT-5.6
- Tightness
- #16.2
GPT-5.6 Luna
- Organization
- OpenAI
- Wave
- July 2026 GPT-5.6
- Tightness
- #24.5
GPT-5.6 Terra
- Organization
- OpenAI
- Wave
- July 2026 GPT-5.6
- Tightness
- #13.1
Grok 4.5
- Organization
- xAI
- Wave
- July 2026 late
- Tightness
- #17.5
Kimi K3
- Organization
- Moonshot AI
- Wave
- July 2026 late
- Tightness
- #17.8
Gemini 3.6 Flash
- Organization
- Wave
- July 2026 late
- Tightness
- #6.8
Claude Opus 5
- Organization
- Anthropic
- Wave
- July 2026 late
- Tightness
- #12.3
11,310 successful runs · elicited April and July 2026 · v4 prompts · 15 runs per model-quantity cell. Code · Raw responses · Paper (PDF)
Code and dataElicited April and July 2026 · 29 models · v4 prompts