SLR-Bench - Hard — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 36 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash (Preview) | 54 |
| 2 | GPT-5 | 50 |
| 3 | GPT-5 Mini (High) | 44 |
| 4 | GPT-5.4 Mini | 28 |
| 5 | GPT-5 Mini (Medium) | 23 |
| 6 | GLM-4.7 FP8 | 23 |
| 7 | Gemini 2.5 Flash | 18 |
| 8 | Gemini 3.1 Flash Lite (High) | 18 |
| 9 | Gemini 2.5 Pro | 16 |
| 10 | GPT-OSS-120B (High) | 15 |
| 11 | O4 Mini | 14 |
| 12 | Gemma 4 31B | 12 |
| 13 | O3 Mini | 10 |
| 14 | Qwen 3.5 35B | 10 |
| 15 | Qwen 3.5 27B | 9 |
Interactive version: aibenchmarks.dev/benchmark?slug=slr-bench-hard · How the rankings work · Data refreshed daily, snapshot 2026-07-12.