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

MCP-Tasks

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

Data verified 36 confirmed releases in the last 30 daysFollow model changes

A Model Context Protocol task benchmark used in Qwen's launch tables to measure practical execution over MCP-style tools and integrations.

Benchmark score on MCP-Tasks — September 18, 2026

We mirror the published score view for MCP-Tasks. Qwen3.5 397B leads the public snapshot at 74.2%, followed by Qwen3.6 Plus (74.1%) and Claude Opus 4.5 (71.8%). We do not use these results to rank models overall.

1Open weights

Qwen3.5 397B

Alibaba

74.2%
Overall 55.09Context 128K
2Proprietary

Qwen3.6 Plus

Alibaba

74.1%
Overall 60.36Context 1M
3Proprietary

Claude Opus 4.5

Anthropic

71.8%
Overall 58.42Context 200K

5 modelsAgenticCurrentDisplay onlyUpdated September 18, 2026

Benchmark score table (5 models)

Score
1
Qwen3.5 397BAlibaba · Open weight
74.2%
2
Qwen3.6 PlusAlibaba · Closed
74.1%
3
Claude Opus 4.5Anthropic · Closed
71.8%
4
GLM-5Z.AI · Open weight
60.8%
5
Kimi K2.5Moonshot AI · Open weight
59.1%

The published MCP-Tasks snapshot places Qwen3.5 397B first at 74.2%. The third row is 2.4 points behind. The broader top-10 range is 15.1 points, so the table still separates the published systems.

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

About MCP-Tasks

Year

2026

Tasks

MCP-integrated tool tasks

Format

Interactive tool-use evaluation

Difficulty

Advanced MCP workflows

MCP-Tasks is distinct from MCP Atlas in the Qwen3.6 comparisons. BenchLM keeps it separate until a fuller public benchmark specification is available because it appears to represent a different task protocol and score scale.

Qwen3.6 launch benchmarks

Freshness and provenance

Version

MCP-Tasks 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 MCP-Tasks measure?

A Model Context Protocol task benchmark used in Qwen's launch tables to measure practical execution over MCP-style tools and integrations.

Which model scores highest on MCP-Tasks?

Qwen3.5 397B by Alibaba currently leads with a score of 74.2% on MCP-Tasks.

How many models are evaluated on MCP-Tasks?

5 AI models have been evaluated on MCP-Tasks on BenchLM.

Compare top models on MCP-Tasks

Qwen3.5 397B vs Qwen3.6 PlusQwen3.6 Plus vs Claude Opus 4.5Claude Opus 4.5 vs GLM-5GLM-5 vs Kimi K2.5
Last updated: September 18, 2026 · BenchLM version MCP-Tasks 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.