TuRTLe Module Completion (NotSoTiny)
TuRTLe module-completion leaderboard on the NotSoTiny benchmark, using formal equivalence and partition coverage over Tiny Tapeout-derived RTL modules.
15rows
functionality_eqvprimary metric
2026-05-06sampled
Metadata
Metrics
Functionality EQV, Syntax, Coverage Mean, Coverage Median
| Rank | Subject | Functionality EQV | Model Match | Provenance | Sampled |
|---|---|---|---|---|---|
| 1 | Kimi-K2.5 | 31.57 | MoonshotAI: Kimi K2.5 moonshotai-kimi-k2.5 | Imported | 2026-05-06 |
| 2 | Gemma-4-31B-it | 29.54 |  Gemma 4 31B google-gemma-4-31b-it | Imported | 2026-05-06 |
| 3 | Qwen3-Coder-480B-A35B-Instruct | 23.43 |  Qwen3 Coder 480B A35B qwen-qwen3-coder | Imported | 2026-05-06 |
| 4 | gpt-oss-120b | 20.90 |  gpt-oss-120b openai-gpt-oss-120b | Imported | 2026-05-06 |
| 5 | DeepSeek-R1-0528 | 20.73 |  R1 0528 deepseek-deepseek-r1-0528 | Imported | 2026-05-06 |
| 6 | Kimi-K2-Instruct-0905 | 19.00 | MoonshotAI: Kimi K2 0905 moonshotai-kimi-k2-0905 | Imported | 2026-05-06 |
| 7 | InCoder-32B | 18.98 | — | Imported | 2026-05-06 |
| 8 | Qwen2.5-72B-Instruct | 14.70 | Qwen2.5 72B Instruct qwen-qwen-2.5-72b-instruct | Imported | 2026-05-06 |
| 9 | InCoder-32B-Thinking | 13.14 | — | Imported | 2026-05-06 |
| 10 | Qwen2.5-14B-Instruct-1M | 12.49 | — | Imported | 2026-05-06 |
| 11 | Qwen2.5-Coder-32B-Instruct | 11.85 | Qwen2.5 Coder 32B Instruct qwen-qwen-2.5-coder-32b-instruct | Imported | 2026-05-06 |
| 12 | Qwen2.5-14B-Instruct | 8.97 | — | Imported | 2026-05-06 |
| 13 | HaVen-CodeQwen | 4.20 | — | Imported | 2026-05-06 |
| 14 | Qwen2.5-7B-Instruct | 3.48 | Qwen2.5 7B Instruct qwen-qwen-2.5-7b-instruct | Imported | 2026-05-06 |
| 15 | OriGen | 3.31 | — | Imported | 2026-05-06 |
No matching rows.