xbench-DeepSearch
Step 3.5 Flash 83.7% leads since February 2026 Step 3.5 Flash 83.7% leads since February 2026 Agents search the web to answer 100 Chinese questions that need multi-step retrieval. Scored by accuracy against reference answers.
A refreshed 100-question set, DeepSearch-2510, followed in October 2025.
- Made by
- xbench (HongShan)
- Released
- May 2025
- Kind
- Deep research
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Strongest model tested
- Kimi K2.5 #75 on the capability index
- Last in a launch post
- February 2026, dropped for a newer version
- Last model added
- February 2026
- Scores refreshed
- November 12th, 2026
Step 3.5 Flash leads with 83.7% among models released by February 2026
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.
Kimi K2.5 leads with 46% across all independent runs
Best score per model across the official leaderboard, Epoch AI’s own runs and any board Epoch AI copied. Each bar and row names its source.
Step 3.5 Flash leads with 83.7%, 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 February 2026, and nobody has reported 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 Step 3.5 Flash 83.7%
- 2 Grok 4 Fast 74%
- 3
MiniMax-M2 72%
Source: Labs’ model cards
Source: Official xbench-DeepSearch leaderboard
- 1 Step 3.5 Flash 83.7%
- 2 Grok 4 Fast 74%
- 3 MiniMax-M2 72%
- 4 Kimi K2.5 Thinking 46%
Sources: Labs’ model cards and official xbench-DeepSearch leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Step 3.5 Flash | 83.7% | Feb 2026 | Lab model card | |
| 2 | Grok 4 Fast | 74% | Sep 2025 | Lab model card | |
| 3 | MiniMax-M2 | 72% | Oct 2025 | Lab model card |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Kimi K2.5 | 46% | Thinking | Jan 2026 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Step 3.5 Flash | 83.7% | Feb 2026 | Lab model card | |
| 2 | Grok 4 Fast | 74% | Sep 2025 | Lab model card | |
| 3 | MiniMax-M2 | 72% | Oct 2025 | Lab model card | |
| 4 | Kimi K2.5 | 46% | Thinking | Jan 2026 | Official leaderboard |
The benchmark's own leaderboard has 11 entries, 1 of them models we track. Switch the scores above to rank them together.
2 models have held number one in labs’ own numbers since its release in May 2025 Number one over time 2 models have held number one with claims included since its release in May 2025
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: 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 xbench-DeepSearch leaderboard and labs’ model cards
Labs headline it less often now, last in February 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 |
|---|---|---|---|
| Feb 2, 2026 | Step 3.5 Flash | 83.7 | xbench-DeepSearch (2025.05) |
| Oct 27, 2025 | MiniMax-M2 | 72 | xbench-DeepSearch |
| Sep 19, 2025 | Grok 4 Fast | 74 | X Bench Deepsearch (zh) 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 |
|---|---|---|---|---|
| Feb 11, 2026 | Step 3.5 Flash technical report | 83.7 | xbench-DeepSearch-2505, avg@3 (Table 5) | Capabilities |
Versions
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%