Community
Compare top models
LLM Benchmarks
See how today's leading models write SpacetimeDB code, scored task by task on live modules.
| Model | Eval Pass% ▾ | Checks | Cost | Run Time | Auth | Basics | Data Modeling | Queries | Schema |
|---|---|---|---|---|---|---|---|---|---|
| openai/gpt-5.6-sol | 100.0% | 89/89 | $1.65258.2K tokens | 4m 7s | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% |
| x-ai/grok-4.5 | 100.0% | 89/89 | $0.73301.1K tokens | 6m 34s | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% |
| Gemini 3.1 Pro | 100.0% | 89/89 | $1.28333.4K tokens | 7m 39s | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% |
| anthropic/claude-opus-5 | 98.9% | 88/89 | $2.39413.1K tokens | 3m 42s | 100.0% | 96.7% | 100.0% | 100.0% | 100.0% |
| anthropic/claude-fable-5 | 98.9% | 88/89 | $4.80413.5K tokens | 5m 3s | 100.0% | 100.0% | 100.0% | 87.5% | 100.0% |
| anthropic/claude-sonnet-5 | 98.9% | 88/89 | $0.96413.4K tokens | 3m 31s | 100.0% | 96.7% | 100.0% | 100.0% | 100.0% |
| google/gemini-3-flash-preview | 97.8% | 87/89 | $2.29988.6K tokens | 61m 15s | 100.0% | 96.7% | 100.0% | 87.5% | 100.0% |
| DeepSeek V4 Pro | 97.8% | 87/89 | $0.15294.5K tokens | 12m 50s | 100.0% | 96.7% | 100.0% | 87.5% | 100.0% |
| openai/gpt-5.6-terra | 97.8% | 87/89 | $0.31255.6K tokens | 1m 53s | 100.0% | 93.3% | 100.0% | 100.0% | 100.0% |
| moonshotai/kimi-k3 | 97.8% | 87/89 | $0.92258.6K tokens | 5m 57s | 100.0% | 96.7% | 100.0% | 87.5% | 100.0% |
| DeepSeek V4 Flash | 96.6% | 86/89 | $0.04284.6K tokens | 8m 13s | 100.0% | 90.0% | 100.0% | 100.0% | 100.0% |
| qwen/qwen3-coder-plus | 68.5% | 61/89 | $0.19256.0K tokens | 3m 5s | 75.0% | 93.3% | 83.3% | 62.5% | 45.9% |
| qwen/qwen3-coder-flash | 57.3% | 51/89 | $0.06255.9K tokens | 2m 41s | 75.0% | 83.3% | 83.3% | 50.0% | 29.7% |