Sakana kana-letter reading-order set
Fugu-Ultra (June 2026 paper) 77.6% tops its leaderboard
Not in model cards Model recovers the reading order of 25 expert-annotated classical Japanese kana letters (chirashigaki). Scored by normalized edit distance.
Lab-created in-house eval (Sakana AI). Built because no public benchmark existed. No release link.
- Made by
- Sakana AI
- Released
- June 2026
- Kind
- Documents, charts and text in images
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- Kept private
5
Entries on its own leaderboard, 0 models we track
Fugu-Ultra (June 2026 paper) tops the leaderboard with 77.6%
Best score per entry from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.
- 1 Fugu-Ultra (June 2026 paper) 77.6%
- 2 Anonymous frontier Model A 64.2%
- 3 Fugu (June 2026 paper) 47.3%
- 4 Anonymous frontier Model B 44.9%
- 5 Seed heuristic 11.6%
Source: Official Sakana kana-letter reading-order set leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Fugu-Ultra (June 2026 paper) | 77.6% | Beam search | Official leaderboard | |
| 2 | Anonymous frontier Model A | 64.2% | Beam search | Official leaderboard | |
| 3 | Fugu (June 2026 paper) | 47.3% | Beam search | Official leaderboard | |
| 4 | Anonymous frontier Model B | 44.9% | Beam search | Official leaderboard | |
| 5 | Seed heuristic | 11.6% | Beam search | Official leaderboard |
No lab model card reports it yet
We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.
More in Vision
- MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy. GPT-5.1 85.4%
- MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. GPT-5.6 Sol 84.6%
- CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
- MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy.
Qwen 3.8 Max 97.7% - MMStar In use Models answer 1,500 human-curated image questions that cannot be solved without the image, across 6 core capabilities. Scored by accuracy. Qwen 3.8 Max 85.9%
- ChartQA In use Models answer human-written and generated questions about chart images that need visual and arithmetic reasoning. Scored by relaxed accuracy with a 5 percent numeric tolerance.
Command A Vision 90.9%