Skip to main content
BenchLM
Advertise

Benchmark profile

OSWorld 2.0

A long-horizon computer-use benchmark covering realistic workflows across everyday and professional desktop tasks.

Data verified

Benchmark score on OSWorld 2.0 — July 23, 2026

BenchLM mirrors the published score view for OSWorld 2.0. GPT-5.6 Sol leads the public snapshot at 62.6% , followed by GPT-5.6 Terra (50.2%) and GPT-5.6 Luna (45.6%). BenchLM does not use these results to rank models overall.

1Closed

GPT-5.6 Sol

OpenAI

gpt-5-6-sol

62.6%
Overall 81.96Context 1M
2Closed

GPT-5.6 Terra

OpenAI

gpt-5-6-terra

50.2%
Overall 72.57Context 1M
3Closed

GPT-5.6 Luna

OpenAI

gpt-5-6-luna

45.6%
Overall 67.17Context 1M
12 modelsAgenticCurrentDisplay onlyUpdated July 23, 2026

Benchmark score table (12 models)

Score
1
GPT-5.6 SolOpenAI · Closed
62.6%
2
GPT-5.6 TerraOpenAI · Closed
50.2%
3
GPT-5.6 LunaOpenAI · Closed
45.6%
4
Claude Opus 4.8Anthropic · Closed
20.6%
5
Claude Opus 4.7 (Adaptive)Anthropic · Closed
18.2%
6
Muse Spark 1.1Meta · Closed
14.2%
7
Claude Opus 4.7Anthropic · Closed
13.9%
8
GPT-5.5OpenAI · Closed
13.0%
9
Claude Sonnet 4.6Anthropic · Closed
8.3%
10
Kimi K2.6Moonshot AI · Open weight
4.6%
11
MiniMax M3MiniMax · Open weight
4.6%
12
Qwen3.7 PlusAlibaba · Closed
2.8%

The published OSWorld 2.0 snapshot places GPT-5.6 Sol first at 62.6%. The third row is 17.0 points behind. The broader top-10 range is 58.0 points, so the table still separates the published systems.

12 models have been evaluated on OSWorld 2.0. The benchmark falls in the Agentic category. This category carries a 22% weight in BenchLM.ai's overall scoring system. OSWorld 2.0 is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About OSWorld 2.0

Year

2026

Tasks

108 long-horizon computer-use workflows

Format

Interactive computer-use evaluation

Difficulty

Long-horizon professional workflows

OSWorld 2.0 expands computer-use evaluation to 108 long-horizon workflows that require state tracking, cross-source reasoning, visual-spatial precision, dynamic interaction, and verification. BenchLM stores the primary binary-completion score as a display-only agentic benchmark.

OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks

BenchLM freshness & provenance

Version

OSWorld 2.0 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 OSWorld 2.0 measure?

A long-horizon computer-use benchmark covering realistic workflows across everyday and professional desktop tasks.

Which model scores highest on OSWorld 2.0?

GPT-5.6 Sol by OpenAI currently leads with a score of 62.6% on OSWorld 2.0.

How many models are evaluated on OSWorld 2.0?

12 AI models have been evaluated on OSWorld 2.0 on BenchLM.

Compare Top Models on OSWorld 2.0

GPT-5.6 Sol vs GPT-5.6 TerraGPT-5.6 Terra vs GPT-5.6 LunaGPT-5.6 Luna vs Claude Opus 4.8Claude Opus 4.8 vs Claude Opus 4.7 (Adaptive)
Last updated: July 23, 2026 · BenchLM version OSWorld 2.0 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.