Random Complex Tasks (LongCat)
LongCat-Flash-Thinking-2601 35.8% Fading Agents solve 100 tasks sampled from a generator that builds random executable tool environments across more than four domains. Scored by Avg@4, averaged over three runs.
In-house test of generalization to unseen tool environments. Meituan says it will add it to an open evaluation platform.
- Level
- University Undergraduates and entry-level professionals
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Agent task Many steps in a terminal, browser, desktop, app, game or robot.
LongCat-Flash-Thinking-2601 leads with 35.8%
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | LongCat-Flash-Thinking-2601 | 35.8% | Jan 2026 | Model card |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Labs headline it less often now, last in Jan 2026
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| 14 Jan 2026 | LongCat-Flash-Thinking-2601 | 35.8 | Random Complex Tasks (Avg@4) |
One system card reports it
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 23 Jan 2026 | LongCat-Flash-Thinking-2601 technical report | 35.8 | Random Complex Tasks (Avg@4), mean of 3 runs (Table 2) | Capabilities |
More in Tool use
- AutomationBench In use Agent completes end-to-end business workflows inside a simulated company exposing dozens of REST APIs. Graded on resulting state.
Gemini 4 Carbon 53.9% - MCP Atlas In use Multi-step workflows over real MCP servers. Scores tool-use competency on realistic tasks.
Muse Spark 1.1 88.1% - BFCL V4 In use Models call functions and tools, including multi-turn agentic tasks with web search and memory. Checked against expected calls and outcomes.
Qwen3.7-Max 75% - τ³-bench Banking In use Agents act as banking customer-service reps over many turns with a simulated user, following policy. Pass^1 on the final database state. Qwen 3.8 Max 55.1%
- Claw-Eval In use 300 human-verified agent tasks (service orchestration, multimodal, multi-turn dialogue) audited via traces and snapshots. Rubric scores with Pass^3 consistency. Claude Sonnet 4.6 81.4%
- DeepSearchQA In use Questions that need multi-step search and synthesis. Final answers graded against references. Kimi K3 95%