SpacetimeDB LLM Benchmark (Rust): leaderboard
Rust subset of the SpacetimeDB LLM Benchmark. Tests LLM ability to generate correct SpacetimeDB Rust 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-5.6 Sol | 100 | #19 |
| 2 | GPT-6 Astra | 100 | #6 |
| 3 | Claude Opus 5.5 | 100 | #3 |
| 4 | GPT-6 Sol | 98.4 | #14 |
| 5 | Grok 4.7 | 98.4 | #25 |
| 6 | Claude Opus 5 | 97.9 | #12 |
| 7 | Grok 4.3 | 97.8 | #188 |
| 8 | Grok Build 0.1 | 97.8 | #117 |
| 9 | Claude Fable 5 | 97.4 | #16 |
| 10 | Claude Sonnet 4.6 | 96.6 | #90 |
| 11 | GPT-5.5 | 96.6 | #31 |
| 12 | Claude Opus 4.8 | 94.4 | #37 |
| 13 | Claude Fable 5.1 | 94.2 | #9 |
| 14 | Gemini 3.1 Pro (Preview) | 92.6 | #58 |
| 15 | GPT-5.4 Mini | 92.1 | #212 |
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-rust · How It Works · Data refreshed daily, snapshot 2026-10-20.