AI Model Capability Comparison
Computer use
Only models released within the past year are shown. Only benchmarks covering at least 3 of these models are shown. Unknown release dates are excluded; historical data is retained.
CUA-benchComputer-use agent benchmark
— means no published score for this candidate in this source, not zero.5/11 recent-year models have scores
| No. | Model | Est. API costEstimated API cost for the evaluation | Input costInput price per million tokens | Output costOutput price per million tokens | Time / actionAverage time per action | |
|---|---|---|---|---|---|---|
| 1 |  GPT-6 AstraGPT-6 Astra | 19.17 | $1821.37* | $10 | $50 | 32.09 s |
| 2 |  Claude Opus 5.5Claude Opus 5.5 | 14 | $188.04 | $4 | $20 | 14.71 s |
| 3 | Claude Fable 5.1Claude Fable 5.1 | 13.17 | $323.78 | $10 | $50 | 37.44 s |
| 4 | Claude Opus 5Claude Opus 5 | 9 | $232.23 | $5 | $25 | 25.29 s |
| 5 |  Gemini 4 ArgonGemini 4 Argon | 4.83 | $193.78 | $4 | $20 | 1.18 min |
PandaNpc Updated Oct 21, 2026, 06:01 UTC
Source: Epoch AI, CC BY 4.0 · Vals.ai · Artificial Analysis (artificialanalysis.ai)
Column guide
- No.
- Display order only. Sorting changes this number; it is not a published capability rank.
- Model
- The evaluated model name and its provider icon. A dash in a score column means no published score is available here, not a zero.
- Score
- Tests using a keyboard and mouse to play commercial video games. It measures interactive game control rather than office-software tasks. Evaluation methodology ↗
- Coverage
- Only published results for the selected model families are shown. OSWorld 2.x, Verified and Pro currently supply Claude Opus 5 configurations; this is not complete coverage of every model. Windows Agent Arena, MacArena, ScreenSpot-Pro, OSWorld-Human, WebArena-Verified, VisualWebArena, Online-Mind2Web and WorkArena++ are not yet integrated here. SafeArena measures safety separately and is not merged into task-completion scores. Missing results are never filled with zero.
- Est. API cost
- Estimated API cost for the evaluation · USD
- Input cost
- Input price per million tokens · USD / 1M tokens
- Output cost
- Output price per million tokens · USD / 1M tokens
- Time / action
- Average time per action · s / min
- Vals.ai
- Costs and times are reported by Vals for this benchmark, not universal model prices or latency. CUA-bench estimated API cost covers evaluation usage and is a lower-bound estimate, not cost per task; time per action is an average, not a median. An asterisk marks launch-day prompt-cache behavior that increased cache-write costs. Missing values are unpublished, not zero.