Skip to main content
BenchLM
Advertise

Benchmark profile

JobBench

An occupational agent benchmark for professional workflows that workers say they most want delegated to AI.

Data verified

Benchmark score on JobBench — July 23, 2026

BenchLM mirrors the published score view for JobBench. Muse Spark 1.1 leads the public snapshot at 54.7% , followed by Kimi K3 (52.9%) and Claude Opus 4.7 (Adaptive) (45.9%). BenchLM does not use these results to rank models overall.

1Closed

Muse Spark 1.1

Meta

muse-spark-1-1

54.7%
Overall 77.44Context 1M
2Closed

Kimi K3

Moonshot AI

kimi-3

52.9%
Overall 80.96Context 1.05M
3Closed

Claude Opus 4.7 (Adaptive)

Anthropic

claude-opus-4-7-max

45.9%
Overall 66.27Context 1M
22 modelsAgenticCurrentDisplay onlyUpdated July 23, 2026

Benchmark score table (22 models)

Score
1
Muse Spark 1.1Meta · Closed
54.7%
2
Kimi K3Moonshot AI · Closed
52.9%
3
Claude Opus 4.7 (Adaptive)Anthropic · Closed
45.9%
4
GPT-5.5OpenAI · Closed
42.7%
5
GPT-5.4OpenAI · Closed
38.9%
6
Claude Sonnet 4.6Anthropic · Closed
36.9%
7
Claude Opus 4.6Anthropic · Closed
36.7%
8
GPT-5.2OpenAI · Closed
34.3%
9
GPT-5.3 CodexOpenAI · Closed
33.7%
10
Claude Opus 4.5Anthropic · Closed
32.3%
11
Claude Sonnet 4.5Anthropic · Closed
27.7%
12
GPT-5.1-CodexOpenAI · Closed
26.2%
13
GPT-5.2-CodexOpenAI · Closed
26.0%
14
Claude 4.1 OpusAnthropic · Closed
21.9%
15
Qwen3.5 PlusAlibaba · Closed
18.5%
16
Claude 4 SonnetAnthropic · Closed
18.4%
17
Claude Haiku 4.5Anthropic · Closed
16.0%
18
MiniMax M2.5MiniMax · Closed
14.8%
19
Gemini 3 ProGoogle · Closed
11.4%
20
Gemini 3 FlashGoogle · Closed
11.4%
21
Kimi K2.5Moonshot AI · Open weight
8.7%
22
GPT-5 (high)OpenAI · Closed
8.5%

The published JobBench snapshot places Muse Spark 1.1 first at 54.7%. The third row is 8.8 points behind. The broader top-10 range is 22.4 points, so the table still separates the published systems.

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

About JobBench

Year

2026

Tasks

130 tasks across 35 occupations

Format

Agentic workplace deliverables

Difficulty

Professional multi-source workflows

JobBench evaluates agents on source-grounded workplace tasks across 35 occupations, using heterogeneous reference files and fact-anchored chained rubrics. BenchLM tracks the main-set score as a display-only professional-agent benchmark.

JobBench: Aligning Agent Work With Human Will

BenchLM freshness & provenance

Version

JobBench 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.

FAQ

What does JobBench measure?

An occupational agent benchmark for professional workflows that workers say they most want delegated to AI.

Which model scores highest on JobBench?

Muse Spark 1.1 by Meta currently leads with a score of 54.7% on JobBench.

How many models are evaluated on JobBench?

22 AI models have been evaluated on JobBench on BenchLM.

Compare Top Models on JobBench

Muse Spark 1.1 vs Kimi K3Kimi K3 vs Claude Opus 4.7 (Adaptive)Claude Opus 4.7 (Adaptive) vs GPT-5.5GPT-5.5 vs GPT-5.4
Last updated: July 23, 2026 · BenchLM version JobBench 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.