Public KG record
CLM-8B
Recorded overview
KG-recorded model related to CLM-8B; 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: 约 100K held-out questions 上预训练后 top-1 52.1%
- Benchmarks: 约 100K held-out questions 上中期训练后 top-1 69.2%
- Benchmarks: T-Rex game 上成功率为 5/5
- Benchmarks: BFCL v4 上工具调用成功率为 95.2%
- Benchmarks: WikiRacing 上成功率为 26/30
- Benchmarks: Super Mario 上成功率为 5/5
- Benchmarks: DeepSWE 上验证成功率为 81.6%
- Benchmarks: Terminal-Bench 2.1 上验证成功率为 87.6%
Evidence coverage
The KG currently records 11 known information dimensions and has 6 undocumented dimensions, linked to 1 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- Qwen3-8B — based on
- Jev — competes with
- BFCL v4 — evaluated on
- DeepSWE — evaluated on
- T-Rex game — evaluated on