State Management
Manage State with BLoC
ID: google/flutter-manage-state-with-blocImplement an immutable state management layer using package:flutter_bloc, connecting UI events to business logic with unit tests.
Cross-Model Benchmark Trials
Comparison of agent configurations evaluated on this task:
| Model & Harness | Tooling | Status | Composite Reward | Actions |
|---|---|---|---|---|
|
DeepSeek Coder V2deepseek-cli
|
Baseline | PARTIAL | 0.59 | Inspect Trial Details → |
|
DeepSeek R1deepseek-cli
|
Dart MCP + Skills | PASS | 0.94 | Inspect Trial Details → |
|
GPT 4o Minicodex-agent
|
Baseline | PARTIAL | 0.46 | Inspect Trial Details → |
|
o3codex-agent
|
Dart MCP + Skills | PASS | 0.97 | Inspect Trial Details → |
|
Gemini 3.5 Proantigravity-sdk
|
Dart MCP + Skills | PASS | 0.99 | Inspect Trial Details → |
|
GPT 4ocodex-agent
|
Baseline | PARTIAL | 0.69 | Inspect Trial Details → |
|
Claude 3.5 Haikuclaude-code
|
Baseline | PARTIAL | 0.55 | Inspect Trial Details → |
|
Claude 3.5 Sonnetclaude-code
|
Baseline | PARTIAL | 0.75 | Inspect Trial Details → |
|
GPT 5codex-agent
|
Dart MCP + Skills | PASS | 0.97 | Inspect Trial Details → |
|
Gemini 3.5 Flashantigravity-sdk
|
Dart MCP + Skills | PASS | 0.88 | Inspect Trial Details → |
|
Claude 3.7 Sonnetclaude-code
|
Dart MCP + Skills | PASS | 0.98 | Inspect Trial Details → |
|
Gemini 3.1 Flash Litegemini-cli
|
Baseline | AgentTimeoutError | — (Errored) | Inspect Trial Details → |
|
DeepSeek V3deepseek-cli
|
Baseline | PARTIAL | 0.67 | Inspect Trial Details → |