SpacetimeDB LLM Benchmark (TypeScript): leaderboard
TypeScript subset of the SpacetimeDB LLM Benchmark. Tests LLM ability to generate correct SpacetimeDB TypeScript module code, evaluating basics (reducers, tables, CRUD) and schema patterns against live module execution.
Metric: Eval Pass Rate (%). Source: spacetimedb.com. Saturation forecast: Estimated already saturated. 19 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra | 99.5 | #6 |
| 2 | Claude Opus 5.5 | 99.5 | #3 |
| 3 | GPT-6 Sol | 99.5 | #14 |
| 4 | Grok 4.7 | 99.5 | #25 |
| 5 | GPT-5.6 Sol | 98.9 | #19 |
| 6 | Claude Sonnet 4.6 | 97.8 | #90 |
| 7 | GPT-5.5 | 97.8 | #31 |
| 8 | Claude Opus 4.8 | 97.8 | #37 |
| 9 | Grok 4.3 | 97.8 | #188 |
| 10 | Grok Build 0.1 | 97.8 | #117 |
| 11 | Gemini 3.1 Pro (Preview) | 97.4 | #58 |
| 12 | GPT-5.4 Mini | 96.6 | #212 |
| 13 | Claude Fable 5 | 96.3 | #16 |
| 14 | Claude Fable 5.1 | 95.3 | #9 |
| 15 | Claude Opus 5 | 94.7 | #12 |
No result here: #7 GPT-6.1 Sol, #8 Gemini 4 Argon, #10 Muse Wonder Full.
Interactive version: theaggregate.ai/benchmark?slug=spacetimedb-llm-benchmark-typescript · How It Works · Data refreshed daily, snapshot 2026-10-20.