The terminal for AI research.
Which model wins, what it costs to run, how the numbers moved, and the research that moved them — every figure with a source. Press ⌘K to search.
● live · scores, prices & speed verified against Artificial Analysis · Jul 13, 2026
The frontier — right now
full chart · frontier table · cost calculator →Capability vs price
gold staircase = nothing cheaper is better| # | Model | Cap | $/1M | tok/s |
|---|---|---|---|---|
| 1 | Gemini 3.1 Pro Preview | 97.5 | $4.5 | 140 |
| 2 | GPT-5.6 Luna (max) | 97.1 | $2.25 | 234 |
| 3 | GPT-5.5 | 97.0 | $11.25 | 72 |
| 4 | Claude Sonnet 5 | 96.7 | $4 | 79 |
| 5 | Grok 4.5 | 96.0 | $3 | 110 |
| 6 | GLM-5.2 (max) | 95.9 | $2.15 | 200 |
| 7 | Qwen3.7 Max | 95.0 | $3.75 | 197 |
| 8 | GPT-5.4 | 94.9 | $5.63 | 161 |
| 9 | Claude Fable 5 | 94.9 | $20 | 65 |
| 10 | Kimi K2.6 | 94.9 | $1.71 | 43 |
This week
the full score ledger →Score movers
14 daysGPT-5 mini▼ 14.6
LiveCodeBench: 83.8 → 69.2
GPT-5.5 Instant (May 2026)▲ 8.3
AA Long-Context Reasoning: 55.7 → 64
GPT-5 mini▼ 5.7
AIME: 90.7 → 85
GPT-5 mini▼ 5.1
Humanity's Last Exam: 19.7 → 14.6
GPT-5 mini▼ 4.5
Terminal-Bench Hard: 33.3 → 28.8
GPT-5 mini▼ 4.2
IFBench: 75.4 → 71.2
GPT-5 mini▲ 2.7
τ²-bench: 68.4 → 71.1
Notable papers
all →The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning
▲ 161 on HF · 11d ago
Vidu S1: A Real-Time Interactive Video Generation Model
▲ 127 on HF · 7d ago
RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation
▲ 89 on HF · 9d ago
AlayaWorld: Long-Horizon and Playable Video World Generation
▲ 85 on HF · 9d ago
Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning
▲ 84 on HF · 8d ago
The catalog
cross-linked — every entity connectsRecent activity
full feed →PAPMultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering3d agoPAPOrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers3d agoMDLGLM-5.2-FP83d agoMDLGLM-5.24d agoLDRAA Long-Context Reasoning Leaderboard1mo agoLDRTerminal-Bench Hard Leaderboard1mo agoEVLAA Long-Context Reasoning1mo agoEVLTerminal-Bench Hard1mo ago