RWSearch
Agents search the live web to answer 200 expert-written Chinese questions that need many retrieval steps, filtering and arithmetic. Each question has one objective answer.
60 percent of the questions use facts from 2025. The README leaderboard lists LongCat-Flash-Thinking-2601 at 79.5.
- Made by
- AGI-Eval (Meituan)
- Released
- January 2026
- Kind
- Deep research
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- All public
- Strongest model tested
- GPT-5.2 #50 on the capability index
- Last in a launch post
- July 2026, dropped before it saturated
- Last model added
- July 2026
- Scores refreshed
- November 12th, 2026
GPT-5.2 leads with 82% among models released by January 2026
Best score per model from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best.
GPT-5.2 leads with 82%, claims included
Best score per model from every source, including labs’ own numbers and claims Epoch AI collected from reports and papers. Labs pick their own settings, so a claim can beat an independent run of the same model.
The newest model with a score here came out in January 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- Claude Fable 5.2
-
Gemini 4 Carbon - GPT-6 Astra
- Claude Opus 5.5
- and 16 more
- 1 GPT-5.2 xhigh 82%
- 2
LongCat-Flash-Thinking-2601 79.5% - 3 Claude Opus 4.5 75.5%
- 4 Gemini 3 Pro 74.5%
- 5
DeepSeek-V3.2 thinking 74% - 6 GLM-4.7 thinking 69%
- 7 Kimi K2 Thinking 63%
Source: Official RWSearch leaderboard
- 1 GPT-5.2 xhigh 82%
- 2 LongCat-Flash-Thinking-2601 79.5%
- 3 LongCat-2.0 78.8%
- 4 Claude Opus 4.5 75.5%
- 5 Gemini 3 Pro 74.5%
- 6 DeepSeek-V3.2 thinking 74%
- 7 GLM-4.7 thinking 69%
- 8 Kimi K2 Thinking 63%
Sources: Official RWSearch leaderboard and labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.2 | 82% | xhigh | Dec 2025 | Official leaderboard |
| 2 | LongCat-Flash-Thinking-2601 | 79.5% | Jan 2026 | Official leaderboard | |
| 3 | Claude Opus 4.5 | 75.5% | Nov 2025 | Official leaderboard | |
| 4 | Gemini 3 Pro | 74.5% | Nov 2025 | Official leaderboard | |
| 5 | DeepSeek-V3.2 | 74% | thinking | Dec 2025 | Official leaderboard |
| 6 | GLM-4.7 | 69% | thinking | Dec 2025 | Official leaderboard |
| 7 | Kimi K2 Thinking | 63% | Nov 2025 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.2 | 82% | xhigh | Dec 2025 | Official leaderboard |
| 2 | LongCat-Flash-Thinking-2601 | 79.5% | Jan 2026 | Official leaderboard | |
| 3 | LongCat-2.0 | 78.8% | Jul 2026 | Lab model card | |
| 4 | Claude Opus 4.5 | 75.5% | Nov 2025 | Official leaderboard | |
| 5 | Gemini 3 Pro | 74.5% | Nov 2025 | Official leaderboard | |
| 6 | DeepSeek-V3.2 | 74% | thinking | Dec 2025 | Official leaderboard |
| 7 | GLM-4.7 | 69% | thinking | Dec 2025 | Official leaderboard |
| 8 | Kimi K2 Thinking | 63% | Nov 2025 | Official leaderboard |
Labs report scores for 2 models in their cards. Switch the scores above to rank them together.
Number one over time Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release. We draw one row each for the benchmark’s own leaderboard and what labs claim in their cards.
Sources: Official RWSearch leaderboard and labs’ model cards
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Sources: Official RWSearch leaderboard and labs’ model cards
Labs headline it less often now, last in July 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 |
|---|---|---|---|
| Jul 5, 2026 | LongCat-2.0 | 78.8 | RWSearch |
| Jan 14, 2026 | LongCat-Flash-Thinking-2601 | 79.5 | RW Search (Pass@1) |
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 |
|---|---|---|---|---|
| Jan 23, 2026 | LongCat-Flash-Thinking-2601 technical report | 79.5 | RW Search (Pass@1), no context management (Table 2) | Capabilities |
One lab claim next to the leaderboard
Each score a lab reported for its own model, beside the same model's best score on the leaderboard. Gaps mostly come from different harnesses, effort levels and task subsets. 1 of them match, which usually means one side copied the other. Every benchmark.
| Model | Lab says | Board says | Gap |
|---|---|---|---|
| LongCat-Flash-Thinking-2601 | 79.5% RW Search (Pass@1) | 79.5% Leaderboard | Same |
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. Gemini 4 Argon 90.7%
- 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%
- Toolathlon-Verified In use 108 long-horizon tasks across 32 apps through about 600 MCP tools. Execution-based checkers inspect final environment state. GLM-5.3-Flash 78.4%
- DeepSearchQA In use Questions that need multi-step search and synthesis. Final answers graded against references. Kimi K3 95%