Skip to main content
Radar

Every change to the models you run, with its source and its date. Releases, price changes, retirements, API changes, and incidents.Every change to the models you run, with its source.

Follow model changes
BenchLM

WideResearch

We mirror this table; we do not rank on it.

Data verified 35 confirmed releases in the last 30 daysFollow model changes

A broad research-agent benchmark for open-ended information gathering, synthesis, and answer construction across wide search spaces.

Benchmark score on WideResearch — September 18, 2026

We mirror the published score view for WideResearch. Mercury 2 leads the public snapshot at 92.3%, followed by Hy4 preview (83.9%) and Qwen3.8 Max (81.9%). We do not use these results to rank models overall.

1Proprietary

Mercury 2

Inception

92.3%
Overall 42.17Context 128K
2Open weights

Hy4 preview

Tencent

83.9%
Overall 60.89Context 1M
3Open weights

Qwen3.8 Max

Alibaba

81.9%
Overall 73.17Context 1M

16 modelsAgenticCurrentDisplay onlyUpdated September 18, 2026

Benchmark score table (16 models)

Score
1
Mercury 2Inception · Closed
92.3%
2
Hy4 previewTencent · Open weight
83.9%
3
Qwen3.8 MaxAlibaba · Open weight
81.9%
4
Atria Dawn PreviewShanghai Artificial Intelligence Laboratory · Open weight
81.9%
5
Kimi K2.6Moonshot AI · Open weight
80.8%
6
Ornith-1.5-397BOrnith AI · Open weight
80.8%
7
dots3-note PreviewDots Studio · Open weight
78.9%
8
Claude Opus 4.5Anthropic · Closed
76.4%
9
Qwen3.6 PlusAlibaba · Closed
74.3%
10
Qwen3.5 397BAlibaba · Open weight
74.0%
11
Ling 3.0 FlashInclusionAI · Open weight
73.6%
12
Kimi K2.5Moonshot AI · Open weight
72.7%
13
GLM-5Z.AI · Open weight
69.8%
14
Ornith-1.5-35B-A3BOrnith AI · Open weight
67.8%
15
Qwen3.6-35B-A3BAlibaba · Open weight
60.1%
16
Ornith-1.5-9BOrnith AI · Open weight
59.5%

The published WideResearch snapshot places Mercury 2 first at 92.3%. The third row is 10.4 points behind. The broader top-10 range is 18.3 points, so the table still separates the published systems.

16 models have been evaluated on WideResearch. The benchmark falls in the Agentic category. This category carries a 22% weight in BenchLM.ai's overall scoring system. WideResearch is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About WideResearch

Year

2026

Tasks

Open-ended research tasks

Format

Multi-source research evaluation

Difficulty

Broad research-agent workflows

WideResearch evaluates whether a model can sustain a research process over multiple sources and branches rather than answering from shallow retrieval. BenchLM tracks it as a display-only browsing and synthesis benchmark.

Qwen3.6 launch benchmarks

Freshness and provenance

Version

WideResearch 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Questions

What does WideResearch measure?

A broad research-agent benchmark for open-ended information gathering, synthesis, and answer construction across wide search spaces.

Which model scores highest on WideResearch?

Mercury 2 by Inception currently leads with a score of 92.3% on WideResearch.

How many models are evaluated on WideResearch?

16 AI models have been evaluated on WideResearch on BenchLM.

Compare top models on WideResearch

Mercury 2 vs Hy4 previewHy4 preview vs Qwen3.8 MaxQwen3.8 Max vs Atria Dawn PreviewAtria Dawn Preview vs Kimi K2.6
Last updated: September 18, 2026 · BenchLM version WideResearch 2026

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.