PRISM (1C:Enterprise) - Platform Tasks (B): leaderboard
PRISM (genlab-1c) benchmarks code generation in 1C:Enterprise's BSL language over 35 tasks. Category B is platform tasks (FIFO, stock balances, prices, costing, currencies) executed in headless 1C against a synthetic database; the score is the percentage fully solved, higher is better.
Metric: 1C platform tasks fully solved, run in headless 1C (%). Source: prism.genlab-1c.ru. Saturation forecast: Around February 2027. 65 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5.5 | 100 | #3 |
| 2 | GPT-5.6 Sol | 95 | #22 |
| 3 | GPT-6 Astra | 95 | #6 |
| 4 | GPT-6 Sol | 95 | #19 |
| 5 | GPT-6.1 Sol | 90 | #7 |
| 6 | Grok 4.3 | 90 | #204 |
| 7 | Kimi K3.1 Pro | 90 | #17 |
| 8 | GPT-6.1 Pro Sol | 90 | #11 |
| 9 | Gemini 3.1 Pro (Preview) | 85 | #64 |
| 10 | Claude Opus 4.8 | 85 | #39 |
| 11 | MiniMax-M3 | 85 | #151 |
| 12 | Kimi K3 | 85 | #35 |
| 13 | Gemini 3.5 Flash | 85 | #66 |
| 14 | Claude Opus 5 | 85 | #16 |
| 15 | Gemini 3.8 Flash | 85 | #30 |
No result here: #10 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=prism-1c-enterprise-platform-tasks-b · How It Works · Data refreshed daily, snapshot 2026-11-05.