WRBench
已接入
WRBench — 指标、依赖与运行命令。
简介
Natural-25 camera intervention benchmark for persistent visual world state.
WorldFoundry 评测路径: 通过仓内 vendored official pipeline,对生成产物执行或归一化官方 benchmark 流程。 候选模型输出从 generated-artifact 目录读取。
集成状态
| 项目 | 当前状态 |
|---|---|
| Catalog integration | integrated |
| Runner verification | pending |
| Leaderboard | 暂不可用于 leaderboard 声明 |
指标
Task YAML
worldfoundry/data/benchmarks/tasks/external/wrbench.yaml
Primary
wrbench_average
| Metric | 关注点 |
|---|---|
d1_cam_prec | 官方 Requested-camera precision (D1-CamPrec) 指标在 benchmark 协议中的计分结果。 |
d1_cam_align_common_yaw | 官方 Prompt-camera alignment (common yaw) 指标在 benchmark 协议中的计分结果。 |
d1_cam_align_static_hold | 官方 Prompt-camera alignment (static hold) 指标在 benchmark 协议中的计分结果。 |
d2_visual_integrity | 官方 Visual integrity (D2) 指标在 benchmark 协议中的计分结果。 |
d3_visible_spatial_consistency | 官方 Visible spatial consistency (D3) 指标在 benchmark 协议中的计分结果。 |
d4_visible_state_consistency | 官方 Visible state consistency (D4) 指标在 benchmark 协议中的计分结果。 |
d5_reobservation_spatial_consistency | 官方 Re-observation spatial consistency (D5) 指标在 benchmark 协议中的计分结果。 |
d6_reobservation_state_consistency | 官方 Re-observation state consistency (D6) 指标在 benchmark 协议中的计分结果。 |
wrbench_average | 汇总 WRBench diagnostic average 相关子指标后的 benchmark 总分。 |
环境准备
运行环境
- Conda 环境:
worldfoundry-unified-cu128。 - 单独配置: 默认复用 WorldFoundry 统一环境(
needs_new_env: false),通常不需要额外 benchmark-only conda env。 - Contract, Natural-25 request materialization, published-result normalization, and WRBench source are available in-tree.
- Full D1-D6 execution requires external checkpoint paths in WORLDFOUNDRY_WRBENCH_RUNTIME_CONFIG.
测评数据
worldfoundry/evaluation/tasks/execution/runners/wrbench/runtime/wrbenchworldfoundry/data/benchmarks/assets/wrbench/natural25worldfoundry/data/benchmarks/tasks/external/wrbench.yaml
Checkpoint 与资产
- Base-model / metric 依赖:
vggt_omega,dinov2,qwen3_5_vl,qwen3_vl。 - Metric / evaluator checkpoint 默认路径与覆盖变量见 local assets 指南。
关键环境变量
WORLDFOUNDRY_WRBENCH_ROOTWORLDFOUNDRY_WRBENCH_ASSETS_ROOTWORLDFOUNDRY_WRBENCH_RESULTS_PATHWORLDFOUNDRY_GENERATED_ARTIFACT_DIRWORLDFOUNDRY_WRBENCH_VIDEO_MANIFESTWORLDFOUNDRY_WRBENCH_RUNTIME_CONFIG
环境检查
PYTHONPATH=. ${WORLDFOUNDRY_UNIFIED_PYTHON:-python} worldfoundry/evaluation/tasks/execution/runners/wrbench/run_wrbench_official_runner.py --run-fixture --output-dir tmp/worldfoundry_preflight/wrbench --json运行评测
准备好该 benchmark 页面列出的资产和候选产物后,使用下面的公开运行入口。
设置候选产物目录
export WORLDFOUNDRY_GENERATED_ARTIFACT_DIR=/path/to/generated/artifacts导入已有官方结果
worldfoundry-eval zoo benchmark-run \
--benchmark-id wrbench \
--mode normalizer \
--official-results-path /path/to/official/results-or-report \
--generated-artifact-dir "${WORLDFOUNDRY_GENERATED_ARTIFACT_DIR}" \
--output-dir tmp/wrbench/normalizer \
--json从生成产物重新打分
worldfoundry-eval zoo benchmark-run \
--benchmark-id wrbench \
--mode official-run \
--generated-artifact-dir "${WORLDFOUNDRY_GENERATED_ARTIFACT_DIR}" \
--output-dir tmp/wrbench/official-run \
--json直接调用仓内 runner
${WORLDFOUNDRY_UNIFIED_PYTHON:-python} worldfoundry/evaluation/tasks/execution/runners/wrbench/run_wrbench_official_runner.py --benchmark-id wrbench --run-official --output-dir "$WORLDFOUNDRY_BENCHMARK_OUTPUT_DIR" --generated-artifact-dir "$WORLDFOUNDRY_GENERATED_ARTIFACT_DIR" --json依赖与产物
Inputs
- in-tree WRBench runtime and Natural-25 assets
- generated videos and camera sidecars for a new model evaluation
- WRBench scorer runtime configuration for full D1-D6 execution
Outputs
scorecard.jsonbenchmark_contract.jsonraw_metric_table.jsonlper_sample_scores.jsonlgeneration_requests.jsonl