MAP-Neo-7B-Instruct-v0.1: benchmark results
Provider: Other.
Aggregate Rating 1361 ± 28, rank #7397 of 10916 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| KOR-Bench - Operation | 38.4 | Accuracy (%; zero-shot, 250 questions) | 27 |
| KOR-Bench - Puzzle | 1.6 | Accuracy (%; zero-shot, 250 questions) | 16.2 |
| KOR-Bench - Cipher | 2 | Accuracy (%; zero-shot, 250 questions) | 13.5 |
| KOR-Bench - Logic | 10.4 | Accuracy (%; zero-shot, 250 questions) | 13.5 |
| KOR-Bench | 18.16 | Accuracy (%; zero-shot, 1,250 questions) | 8.1 |
| KOR-Bench - Counterfactual | 38.4 | Accuracy (%; zero-shot, 250 questions) | 5.4 |
| SuperGPQA | 17.05 | Accuracy (%) | 2.9 |
Interactive version: theaggregate.ai/model?slug=map-neo-7b-instruct-v0-1 · How It Works · Data refreshed daily, snapshot 2026-11-08.