Model card
Qwen3.5-397B-A17B†.
Anthropic/OpenAIapi
Imported from https://raw.githubusercontent.com/GAIR-NLP/AcademiClaw/main/README.md
§ 02 · Benchmarks
Every benchmark Qwen3.5-397B-A17B† has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | AcademiClaw | Agentic AI · Task agents | avg-score | 64.7% | #4 | 2026-05-04 | source ↗ |
| 02 | AcademiClaw | Agentic AI · Task agents | tool-calls-per-task | 26.0% | #4 | 2026-05-04 | source ↗ |
| 03 | AcademiClaw | Agentic AI · Task agents | avg-tokens-per-task-k | 970.00 | #5 | 2026-05-04 | source ↗ |
| 04 | AcademiClaw | Agentic AI · Task agents | pass | 40.0% | #5 | 2026-05-04 | source ↗ |
| 05 | AcademiClaw | Agentic AI · Task agents | safety-score | 80.8% | #5 | 2026-05-04 | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area
Where Qwen3.5-397B-A17B† actually performs.
§ 04 · Papers
1 paper with results for Qwen3.5-397B-A17B†.
- 2026-05-04· Agentic AI· 5 results
AcademiClaw: When Students Set Challenges for AI Agents
Junjie Yu, Pengrui Lu, Weiye Si, Hongliang Lu et al.
§ 05 · Related models
Other Anthropic/OpenAI models scored on Codesota.
§ 06 · Sources & freshness
Where these numbers come from.
paper
5
results
5 of 5 rows marked verified.