Mathematical Optimization on Signal Processing
73.51Average ScoreEvoX
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| EvoXLLM Backbone=Gemini-3.0-Pro2026.02 | 73.51 | 74.29 | — | |
| EvoXLLM Backbone=GPT-52026.02 | 71.06 | 72.14 | — | |
| AdaEvolveBackbone=GPT-52026.02 | 69.8 | 71.8 | — | |
| GEPALLM Backbone=GPT-52026.02 | 68.91 | 70.57 | — | |
| GEPABackbone=GPT-52026.02 | 68.9 | 70.5 | — | |
| GEPABackbone=Gemini-3-Pro2026.02 | 61.7 | 68 | — | |
| GEPALLM Backbone=Gemini-3.0-Pro2026.02 | 61.69 | 67.98 | — | |
| AdaEvolveBackbone=Gemini-3-Pro2026.02 | 59.3 | 60.3 | — | |
| OpenEvolveBackbone=GPT-52026.02 | 56.9 | 62.2 | — | |
| OpenEvolveLLM Backbone=GPT-52026.02 | 56.86 | 62.19 | — | |
| OpenEvolveBackbone=Gemini-3-Pro2026.02 | 55.3 | 56.5 | — | |
| OpenEvolveLLM Backbone=Gemini-3.0-Pro2026.02 | 55.25 | 56.49 | — | |
| ShinkaLLM Backbone=GPT-52026.02 | 48.55 | 53.28 | — | |
| ShinkaEvolveBackbone=GPT-52026.02 | 48.5 | 53.3 | — | |
| ShinkaEvolveBackbone=Gemini-3-Pro2026.02 | 48 | 50.5 | — | |
| ShinkaLLM Backbone=Gemini-3.0-Pro2026.02 | 47.99 | 50.49 | — | |
| CORALagent_framework=Claude Code, backbone=Opus 4.6, budget_per_task=$502026.07 | — | — | 74.03 | |
| EvoXiterations=100, backbone=Opus 4.62026.07 | — | — | 71.81 | |
| SOTA2026.07 | — | — | 82.29 | |
| SwarmResearchagent_framework=Claude Code, backbone=Opus 4.6, budget_per_task=$502026.07 | — | — | 79.7 |