Vals CUA-bench (CUA-bench)
We show this table for reference; we do not rank on it.
A Vals AI computer-use benchmark in which agents play six commercial video games with a keyboard and mouse.
Evaluation results published by Vals AI. Published leaderboard aggregates and evaluation settings only. Dataset contents are not included.
CUA-bench score on CUA-bench — October 13, 2026
We mirror the published cua-bench score view for CUA-bench. GPT-6 Astra leads the public snapshot at 19.17%, followed by Claude Opus 5.5 (14.00%) and Claude Fable 5.1 (13.17%). We do not use these results to rank models overall.
GPT-6 Astra
OpenAI
codex · max reasoning
codex
Claude Opus 5.5
Anthropic
claude-code · max reasoning
claude-code
Claude Fable 5.1
Anthropic
claude-code · max reasoning
claude-code
9 modelsAgenticCurrentDisplay onlyUpdated October 13, 2026
CUA-bench score table (9 models)
| Rank | Model / configuration | Score | Parameters (B) | Open / closed |
|---|---|---|---|---|
| 1 | GPT-6 AstraOpenAIcodex · max reasoningcodex | 19.17% | Not reported | Closed |
| 2 | Claude Opus 5.5Anthropicclaude-code · max reasoningclaude-code | 14.00% | Not reported | Closed |
| 3 | Claude Fable 5.1Anthropicclaude-code · max reasoningclaude-code | 13.17% | Not reported | Closed |
| 4 | Claude Opus 5Anthropicclaude-code · max reasoningclaude-code | 9.00% | Not reported | Closed |
| 5 | GPT-5.6 SolOpenAIcodex · max reasoningcodex | 8.33% | Not reported | Closed |
| 6 | Muse WonderMetamuse-code · max reasoningmuse-code | 7.17% | Not reported | Closed |
| 7 | Muse Spark 1.3 Maxmetamuse-code · max reasoningmuse-code | 5.83% | Not reported | Unknown |
| 8 | Gemini 4 ArgonGoogleantigravity · high reasoningantigravity | 4.83% | Not reported | Closed |
| 9 | Gemini 3.8 FlashGooglegoogle-computer-use · high reasoninggoogle-computer-use | 4.17% | Not reported | Closed |
How CUA-bench is shown here
BenchLM mirrors the public Vals AI CUA-bench leaderboard captured from https://www.vals.ai/benchmarks/cua_bench and updated by Vals on October 13, 2026. The snapshot preserves overall scores, uncertainty, latency, cost-per-test metadata, and task-level scores where Vals publishes them.
CUA-bench is display only on BenchLM. Vals proprietary or Vals-hosted aggregate views are useful context, but BenchLM does not use them as weighted ranking inputs or as a replacement for benchmark-native source records.
Snapshot
The published CUA-bench snapshot places GPT-6 Astra first at 19.17%. The third row is 6.00 points behind. The broader top-10 range is 15.00 points, so the table still separates the published systems.
9 models have been evaluated on CUA-bench. The benchmark falls in the Agentic category. We keep external benchmark mirrors separate from the weighted global scoring system, so these results remain source-specific evidence. CUA-bench is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About CUA-bench
Year
2026
Tasks
Six commercial video-game control tasks, including held-out games
Format
Overall score with game-level task splits
Difficulty
Keyboard-and-mouse computer use in real-time games
The public beta table reports overall and task-level scores for Minecraft, SUPERHOT, eFootball, and three held-out games. Each result pairs a model with a provider-specific computer-use harness, while the task set remains private, so this board is display-only and excluded from weighted model rankings.
Freshness and provenance
Version
CUA-bench 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
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 CUA-bench measure?
A Vals AI computer-use benchmark in which agents play six commercial video games with a keyboard and mouse.
Which model leads the published CUA-bench snapshot?
GPT-6 Astra currently leads the published CUA-bench snapshot with 19.17% cua-bench score. BenchLM shows this benchmark for display only and does not use it in overall rankings.
How many models are evaluated on CUA-bench?
The October 13, 2026 snapshot contains 9 AI models.
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 7,000+ subscribers.
One email each week. Unsubscribe anytime.