AI Model Capability Comparison
Browser 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.
— means no published score for this candidate in this source, not zero.9/11 recent-year models have scores
| No. | Model | Agent engine | |
|---|---|---|---|
| 1 |  Claude Opus 5.5claude-opus-5-5 | Claude Code | 89 |
| 2 |  GPT-6 Astragpt-6-astra | Codex | 87 |
| 3 | Claude Fable 5.1claude-fable-5-1 | Claude Code | 84 |
| 4 | GPT-6.1 Solgpt-6.1-sol | Codex | 79 |
| 5 | Claude Sonnet 5.5claude-sonnet-5-5 | Claude Code | 79 |
| 6 | Claude Opus 5claude-opus-5 | Claude Code | 78 |
| 7 | GPT-6 Solgpt-6-sol | Codex | 76 |
| 8 | GPT-6 Lunagpt-6-luna | Codex | 74 |
| 9 | Claude Haiku 5.5claude-haiku-5-5 | Claude Code | 74 |
Browserbase / Stagehand
Source: Browserbase / Stagehand ↗
Browserbase Benchmark v2 · Claude Code · Source date unknown
Browserbase Benchmark v2 · Codex · Source date unknown
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.
- Agent engine
- Claude Code · Codex
- Score
- Browserbase / Stagehand browser task accuracy (%). Each row identifies a model and its agent engine. Different engines can affect the result, so scores must not be attributed to the model alone. Sorted by score by default. Evaluation methodology ↗