xbench-DeepSearch-2510

GPT-5 Pro 79% leads since October 2025

Fading

Labs’ own numbers All independent runs Include claimed scores

Agents answer 100 new Chinese deep search questions that need many web searches and cross-checks. Answers are matched to a key.

The dataset is encrypted against crawling. Scores are much lower than on the 2505 set, so the two are not comparable.

Made by: xbench (HongShan)
Released: October 2025
Kind: Deep research
Level: Expert
Scored: Checked automatically
Answers: Short answer
Tasks: All public

Strongest model tested: GPT-5 Pro #63 on the capability index
Last in a launch post: February 2026, dropped before it saturated
Last model added: February 2026
Scores refreshed: November 12th, 2026

Model scored in lab cards

Launch post lists it, from 1 lab

System card reports it, from 1 lab

Step 3.5 Flash leads with 56.3%

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.

GPT-5 Pro leads with 79% 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.

GPT-5 Pro leads with 79%, 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.

Bars Table

56.3 Step 3.5 Flash

1 Step 3.5 Flash 56.3%

Source: Labs’ model cards

1 GPT-5 Pro 79%
2 Kimi K2.5 thinking 46%

Source: Official xbench-DeepSearch-2510 leaderboard

Sources: Official xbench-DeepSearch-2510 leaderboard and labs’ model cards

#	Model	Score	Setting	Date	Source
1	Step 3.5 Flash	56.3%		Feb 2026	Lab model card

#	Model	Score	Setting	Date	Source
1	GPT-5 Pro	79%		Oct 2025	Official leaderboard
2	Kimi K2.5	46%	thinking	Jan 2026	Official leaderboard

#	Model	Score	Setting	Date	Source
1	GPT-5 Pro	79%		Oct 2025	Official leaderboard
2	Step 3.5 Flash	56.3%		Feb 2026	Lab model card
3	Kimi K2.5	46%	thinking	Jan 2026	Official leaderboard

The benchmark's own leaderboard has 11 entries, 2 of them models we track. Switch the scores above to rank them together.

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard Reported by the lab in its model card

Sources: Official xbench-DeepSearch-2510 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.

StepFun

Date	Launch post	Score	As the post writes it
Feb 2, 2026	Step 3.5 Flash	56.3	xbench-DeepSearch (2025.10)

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	56.3	xbench-DeepSearch-2510, avg@3 (Table 5)	Capabilities

Versions

Replaces xbench-DeepSearch