LiveFMBench - 2025: leaderboard
The contamination-aware split of LiveFMBench (2026): 360 C programs newly collected from SV-COMP 2025, for which a model must write ACSL specifications that let Frama-C prove the embedded assertions. The score is pass@1 (%) over 32 samples under direct prompting, counting a sample only when the proof succeeds and the model left the original code and assertions unchanged; higher is better.
Metric: Pass@1 (%) after the faithfulness check on LiveFMBench-2025 (360 C programs from SV-COMP 2025), direct prompting (instructions plus the C program), 32 samples at temperature 0.7 and top-p 0.95, pass@1 estimated from the 32 samples with the unbiased estimator; a sample counts only when Frama-C/WP (Alt-Ergo and Z3) proves the program and its code and assertions are unchanged (faithfulness check); higher is better. Source: arxiv.org. Saturation forecast: Around May 2027. 11 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | DeepSeek R1 0528 | 15.73 | #428 | |
| 2 | DeepSeek V3.1 Terminus | Thinking | 13.64 | #437 |
| 3 | GLM-4.6 | 12.3 | #498 | |
| 4 | Qwen 3 32B | 7.44 | #972 | |
| 5 | Qwen 3 235B A22B 2507 (Thinking) | 7.38 | #466 | |
| 6 | Kimi K2 0905 | 6.32 | #570 | |
| 7 | DeepSeek V3.2 | Thinking | 4.65 | #419 |
| 8 | Qwen 3 Coder 480B A35B Instruct | 4.55 | #652 | |
| 9 | Qwen 3 235B A22B 2507 Instruct | 1.89 | #616 | |
| 10 | DeepSeek V3 (0324) | 1.28 | #715 | |
| 11 | Llama 3.3 70B Instruct | 0.25 | #1385 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=livefmbench-2025 · How It Works · Data refreshed daily, snapshot 2026-11-21.