Public KG record
JOLT
Recorded overview
KG-recorded mechanism related to JOLT; detailed English notes are not yet available.
An evidence-backed entity from the project knowledge graph; detailed tool metadata is still being added.
Recorded details
- Benchmarks: 在GSM8K、MATH、LiveCodeBench v6、AppWorld和Terminal-Bench 2.1上测试
- Benchmarks: MATH 上准确率为 72.14%，高于 GRPO 的 68.36%
- Benchmarks: 在文中测试的每个设置中均取得最高平均分
- Benchmarks: AppWorld state-test pass rate 为 72.09%，GRPO 为 62.20%
- Benchmarks: 在每个测试设置中均取得最高平均分
- Benchmarks: AppWorld
- Benchmarks: GSM8K
- Benchmarks: LiveCodeBench v6
Evidence coverage
The KG currently records 9 known information dimensions and has 10 undocumented dimensions, linked to 1 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- NVIDIA — develops
- Perplexity — develops
- GRPO — competes with
- On-Policy Self-Distillation — based on
- GRPO — competes with