Skip to main content
BenchLM

APEX-Agents

We show this table for reference; we do not rank on it.

Data verified 34 confirmed releases in the last 30 daysFollow model changes

A professional-services agent benchmark covering long-horizon knowledge-work tasks.

Benchmark score on APEX-Agents — September 27, 2026

We compile the APEX-Agents rows from provider self-reports and secondary reports. Grok 4.6 leads the table at 57.5%, followed by Apodex 1.1 (38.5%) and Step 5 Preview (37.8%). We do not use these results to rank models overall.

1Proprietary

Grok 4.6

xAI

57.5%
Overall 69.19Context 500K
2Proprietary

Apodex 1.1

Apodex

38.5%
Overall 48.97Context N/A
3Proprietary

Step 5 Preview

StepFun

37.8%
Context 1M

10 modelsAgenticCurrentDisplay onlyUpdated September 27, 2026

Benchmark score table (10 models)

Score
1
Grok 4.6xAI · Closed
57.5%
2
Apodex 1.1Apodex · Closed
38.5%
3
Step 5 PreviewStepFun · Closed
37.8%
4
Kimi K3Moonshot AI · Closed
37.6%
5
Hy4 previewTencent · Open weight
37.1%
6
dots3-note PreviewDots Studio · Open weight
30.8%
7
Ling 3.0 Flash FinInclusionAI · Closed
29.2%
8
Apodex 1.1 MiniApodex · Open weight
27.7%
9
Solar Pro 4Upstage · Closed
18.7%
10
Solar Open 2Upstage · Open weight
16.6%

Among the reported APEX-Agents rows, Grok 4.6 is first at 57.5%. The third row is 19.7 points behind. The broader top-10 range is 40.9 points, so the table still separates the published systems.

10 models have been evaluated on APEX-Agents. The benchmark falls in the Agentic category. APEX-Agents is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About APEX-Agents

Year

2026

Tasks

Professional-services agent tasks

Format

Agent task-completion score

Difficulty

Long-horizon professional work

BenchLM stores Moonshot's provider-run APEX-Agents value separately from the Artificial Analysis APEX-Agents-AA implementation.

Kimi K3: Open Frontier Intelligence

Freshness and provenance

Version

APEX-Agents 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 APEX-Agents measure?

A professional-services agent benchmark covering long-horizon knowledge-work tasks.

Which model scores highest on APEX-Agents?

Grok 4.6 by xAI currently leads with a score of 57.5% on APEX-Agents.

How many models are evaluated on APEX-Agents?

10 AI models have been evaluated on APEX-Agents on BenchLM.

Compare top models on APEX-Agents

Grok 4.6 vs Apodex 1.1Apodex 1.1 vs Step 5 PreviewStep 5 Preview vs Kimi K3Kimi K3 vs Hy4 preview
Last updated: September 27, 2026 · BenchLM version APEX-Agents 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.