PRISM (1C:Enterprise) - Algorithmic Tasks (A): leaderboard
PRISM (genlab-1c) benchmarks code generation in 1C:Enterprise's BSL language over 35 tasks. Category A is algorithmic tasks in pure BSL executed in OneScript; the score is the percentage of tasks fully solved, higher is better, in coarse steps.
Metric: Algorithmic BSL tasks fully solved, run in OneScript (%). Source: prism.genlab-1c.ru. Saturation forecast: Estimated already saturated. 65 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Sol | 100 | #22 |
| 2 | Kimi K3 | 100 | #35 |
| 3 | Claude Opus 5 | 100 | #16 |
| 4 | Gemini 3.8 Flash | 100 | #30 |
| 5 | GLM-5.3 | 100 | #44 |
| 6 | Gemini 3.7 Flash | 100 | #24 |
| 7 | Kimi K3.1 Pro | 100 | #17 |
| 8 | Gemini 3.1 Pro (Preview) | 93 | #64 |
| 9 | GPT-5.5 | 93 | #33 |
| 10 | Gemini 3.5 Flash | 93 | #66 |
| 11 | GPT-6 Astra | 93 | #6 |
| 12 | Claude Opus 5.5 | 93 | #3 |
| 13 | MiMo-V2.5-Pro | 93 | #167 |
| 14 | Gemini 4 Argon | 93 | #9 |
| 15 | Claude Sonnet 5.5 | 93 | #14 |
No result here: #10 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=prism-1c-enterprise-algorithmic-tasks-a · How It Works · Data refreshed daily, snapshot 2026-11-05.