Public KG record
Mellum2.1
Recorded overview
KG-recorded model related to Mellum2.1; 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: LiveCodeBench v6：82.0
- Benchmarks: SWE-bench Verified：47.0
- Benchmarks: Terminal-Bench 2.1：17.4
- Benchmarks: HumanEval+：91.5；MBPP+：79.4；BFCL v4：62.3
- Benchmarks: HarmBench：8.5，较Mellum2的21.5下降
- Benchmarks: LiveCodeBench v6
- Benchmarks: SWE-bench
- Benchmarks: Terminal-Bench 2.1
Evidence coverage
The KG currently records 14 known information dimensions and has 5 undocumented dimensions, linked to 1 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- Mellum2 — based on
- Qwen3.5-9B — competes with
- LiveCodeBench v6 — evaluated on
- SWE-bench — evaluated on
- Terminal-Bench 2.1 — evaluated on