QuantumComputing
Task 32 / 47
task_02_clifford_t_synthesis
Clifford+T synthesis: realize a target unitary or subcircuit with fewer T gates, lower T-depth, or cheaper total gate count. The benchmark scores against reference costs relevant to fault-tolerant quantum computing, emphasizing circuit rewriting and combinatorial optimization in QC toolchains.
Model leaderboard
Updated v1 results · 2026-09-15 · raw score, higher is better.
| # | Participant | Raw score | Medal |
|---|---|---|---|
| 1 | Claude Opus 4.6 | 2.8473466 | Gold |
| 1 | DeepSeek V3.2 | 2.8473466 | Gold |
| 1 | Gemini 3.1 Pro Preview | 2.8473466 | Gold |
| 1 | GPT-5.4 | 2.8473466 | Gold |
| 1 | Grok 4.20 | 2.8473466 | Gold |
| 1 | Qwen3 Coder Next | 2.8473466 | Gold |
| 1 | Seed 2.0 Pro | 2.8473466 | Gold |
| — | GLM-5 | No valid score | — |
Framework results · original paper
Historical results from the original evaluators · normalized score (0–100).
| # | Participant | Score |
|---|---|---|
| 1 | GPT-OSS + ABMCTS | 100.0 |
| 2 | Claude Opus 4.6 + ShinkaiEvolve | 2.4 |
| 3 | Claude Opus 4.6 + OpenEvolve | 0.0 |
| 4 | GPT-OSS + ShinkaiEvolve | 0.0 |
| 5 | Claude Opus 4.6 + ABMCTS | 0.0 |
| 6 | GPT-OSS + OpenEvolve | 0.0 |
Model results use the updated scores and medal thresholds. No valid score earns zero medal credit. Historical framework scores use the original evaluators and have not been updated alongside the model results.