Reflection Beam Safety - ABC-Bench Screening Evasion - Average Score: leaderboard
Computational biological sequence-screening agent tasks,10 sequences,jury rubric score. Average and best-of-three are distinct; timeout counts remain in provenance. Source-specific score; no fusion with a different harness or version is implied. Computational sequence task rubric score; publisher excludes timeouts. Refusals do not change denominator for admitted metric. Metric: Average Score (%). Higher is better. Exact printed figure values; https://cdn.sanity.io/images/sp40emik/production/24fb85302de02b9e6f6fe8a4ec7d3e44c147d1ae-2880x1998.png?w=3840&fit=max
Metric: Average Score (%). Source: reflection.ai. Saturation forecast: Around 2031. 13 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Kimi K3 | 46.18 | #29 |
| 2 | GLM-5.3 | 42.7 | #40 |
| 3 | DeepSeek V4 Pro | 41.71 | #101 |
| 4 | GLM-5.2 | 39.8 | #71 |
| 5 | Kimi K2.6 | 38.48 | #105 |
| 6 | Qwen 3.8 Max | 38.36 | #31 |
| 7 | Muse Glimmer 30B | 36.19 | #178 |
| 8 | DeepSeek V4 Flash | 32.44 | #135 |
| 9 | GPT-OSS-120B | 32.17 | #336 |
| 10 | Inkling | 31.2 | #123 |
| 11 | Beam 1.0 | 27.89 | #97 |
| 12 | Nemotron 3 Ultra | 25.13 | #240 |
| 13 | DeepSeek V4.1 Flash | 25.1 | #35 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #7 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=reflection-beam-safety-abc-bench-screening-evasion-average-score · How It Works · Data refreshed daily, snapshot 2026-10-17.