ASI-Bench (Claude Code): leaderboard
ASI-Bench runs 60 project-level research tasks without external tool access (arXiv 2608.17271v1). Overall Scientific Score is the equal-weight mean of prompt bands B1-B4, macro-averaged over tasks and rounds, 0-100, higher is better. Claude Code harness runs only, from the Apexintelligence-AI/ASI-Bench-Leaderboard Space's app/page.tsx; efforts stay in the label, and two runs report one round.
Metric: Scientific Score (0-100). Source: huggingface.co. Saturation forecast: Around 2028. 13 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5 (Max) | 50.29 | #16 (Claude Opus 5) |
| 2 | Gemini 3.8 Flash | 43.19 | #30 |
| 3 | GLM-5.3 (Max) | 41.65 | #44 (GLM-5.3) |
| 4 | Qwen 3.8 Max (Max) | 38.87 | #34 (Qwen 3.8 Max) |
| 5 | Claude Opus 4.8 (Max) | 37.51 | #39 (Claude Opus 4.8) |
| 6 | Kimi K3 (Max) | 37.09 | #35 (Kimi K3) |
| 7 | GLM-5.2 (Max) | 35.59 | #80 (GLM-5.2) |
| 8 | GLM-5.3 Flash (Max) | 33.52 | #77 (GLM-5.3 Flash) |
| 9 | DeepSeek V4 Flash (Max) | 31.9 | #155 (DeepSeek V4 Flash) |
| 10 | DeepSeek V4 Pro (Max) | 24.98 | #112 (DeepSeek V4 Pro) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=asi-bench-claude-code · How It Works · Data refreshed daily, snapshot 2026-11-05.