SpacetimeDB LLM Benchmark (C#): leaderboard
C# subset of the SpacetimeDB LLM Benchmark. Tests LLM ability to generate correct SpacetimeDB C# module code, evaluating basics (reducers, tables, CRUD) and schema patterns against live module execution.
Metric: Eval Pass Rate (%). Source: spacetimedb.com. 19 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.6 | 98.9 | #90 |
| 2 | GPT-6 Astra | 98.4 | #6 |
| 3 | Gemini 3.1 Pro (Preview) | 97.8 | #58 |
| 4 | Claude Opus 5.5 | 97.4 | #3 |
| 5 | GPT-5.5 | 96.6 | #31 |
| 6 | Claude Opus 4.8 | 96.6 | #37 |
| 7 | Claude Fable 5 | 96.3 | #16 |
| 8 | Grok 4.7 | 96.3 | #25 |
| 9 | GPT-5.6 Sol | 95.8 | #19 |
| 10 | Grok Build 0.1 | 95.5 | #117 |
| 11 | Claude Opus 5 | 94.7 | #12 |
| 12 | Kimi K3 | 93.7 | #30 |
| 13 | Grok 4.3 | 93.3 | #188 |
| 14 | GPT-6 Sol | 93.2 | #14 |
| 15 | Claude Fable 5.1 | 91.6 | #9 |
Interactive version: theaggregate.ai/benchmark?slug=spacetimedb-llm-benchmark-c-sharp · How It Works · Data refreshed daily, snapshot 2026-10-20.