FIKA-Bench: leaderboard
FIKA-Bench (2026) asks for the exact fine-grained identity of a product, species, vehicle, landmark or cultural object in an image, with human-verified evidence for every answer and items kept only when strong closed-book models failed. Closed-book models answer from the image and question alone. Strict accuracy in percent from an LLM judge that accepts only answers at the required granularity; higher is better.
Metric: Overall strict answer accuracy (%) on FIKA-Bench, open-ended fine-grained recognition questions (311 images from decontaminated public fine-grained datasets and real-life photos, each answer backed by human-verified evidence URLs, kept after strong closed-book models failed); a text-only LLM judge counts only answers at the required granularity as correct, closed-book models (no tools, image and question only); higher is better. Source: arxiv.org. Saturation forecast: Around August 2027. 10 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Kimi K2.6 | 25.1 | #192 |
| 2 | Gemini 3.1 Flash Lite | 20.6 | #371 |
| 3 | Qwen 3.5 397B A17B | 18.3 | #264 |
| 4 | GPT-5 Mini | 17.4 | #364 |
| 5 | GLM-5V Turbo | 15.8 | #360 |
| 6 | Qwen 3 VL 235B A22B | 14.8 | #485 |
| 7 | Fine-R1-7B | 11.6 | |
| 8 | Qwen 3.5 9B | 9.3 | #828 |
| 9 | Qwen 3 VL 8B | 9 | #917 |
| 10 | VisualRFT-7B | 6.8 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=fika-bench · How It Works · Data refreshed daily, snapshot 2026-11-21.