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.
- Level
- Expert Specialists with years of training, often over hours of work
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Short answer A number, word or short string matched to a key.
GPT-5.2 leads with 82% among models released by Jan 2026
Best score per model from the benchmark's own leaderboard, read on 2 Nov 2026. Where a model ran with several settings or harnesses, we keep its best.
The newest model with a score here came out in Jan 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6 Astra
- Claude Opus 5.5
- GPT-6.1 Terra
- GPT-6.1 Sol
- 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%
| # | 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 |
Labs report scores for 2 models in their cards. We plot every source in the charts below.
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.
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 Jul 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 |
|---|---|---|---|
| 5 Jul 2026 | LongCat-2.0 | 78.8 | RWSearch |
| 14 Jan 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 |
|---|---|---|---|---|
| 23 Jan 2026 | LongCat-Flash-Thinking-2601 technical report | 79.5 | RW Search (Pass@1), no context management (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%