Optics
Task 24 / 47
fiber_mcs_power_scheduling
Joint MCS and transmit-power scheduling for optical links under time-varying channels or traffic, choosing discrete modulation orders and power levels subject to BLER or latency constraints. Mixed discrete–continuous control mirrors link adaptation in optical access and coherent systems.
Model leaderboard
Updated v1 results · 2026-09-15 · raw score, higher is better.
| # | Participant | Raw score | Medal |
|---|---|---|---|
| 1 | GPT-5.4 | 0.6608371 | Gold |
| 2 | Claude Opus 4.6 | 0.6542 | Silver |
| 3 | GLM-5 | 0.6491 | Bronze |
| 3 | Seed 2.0 Pro | 0.6491 | Bronze |
| 5 | DeepSeek V3.2 | 0.5182 | — |
| 6 | Gemini 3.1 Pro Preview | 0.4796 | — |
| 7 | Grok 4.20 | 0.4557 | — |
| 8 | Qwen3 Coder Next | 0.4458 | — |
Framework results · original paper
Historical results from the original evaluators · normalized score (0–100).
| # | Participant | Score |
|---|---|---|
| 1 | Claude Opus 4.6 + OpenEvolve | 100.0 |
| 2 | Claude Opus 4.6 + ABMCTS | 100.0 |
| 3 | Claude Opus 4.6 + ShinkaiEvolve | 97.4 |
| 4 | GPT-OSS + ShinkaiEvolve | 50.0 |
| 5 | GPT-OSS + OpenEvolve | 0.0 |
| 6 | GPT-OSS + ABMCTS | 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.