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.8/11 recent-year models have scores
| No. | Model | Reasoning effort | Cost / taskAverage cost per task | Median timeMedian task duration | |
|---|---|---|---|---|---|
| 1 |  GPT-6.1 SolGPT-6.1 Sol | medium | 79.6 | $1.3 | 8 min |
| 2 | GPT-6 AstraGPT-6 Astra | medium | 77.9 | $10.77 | 9 min |
| 3 |  Claude Opus 5.5Claude Opus 5.5 | high | 75 | $2.35 | 12 min |
| 4 | GPT-6 SolGPT-6 Sol | medium | 74.4 | $1.02 | 6 min |
| 5 | Claude Sonnet 5.5Claude Sonnet 5.5 | high | 72.7 | $1.53 | 9 min |
| 6 | Claude Fable 5.1Claude Fable 5.1 | high | 72 | $5.19 | 17 min |
| 7 | GPT-6 LunaGPT-6 Luna | medium | 64.3 | $0.077 | 8 min |
| 8 | Claude Haiku 5.5Claude Haiku 5.5 | high | 64.3 | $0.23 | 9 min |
| 9 | Claude Haiku 5.5Claude Haiku 5.5 | medium | 53.4 | $0.092 | 5 min |
Browser Use
Source: Browser Use ↗ · Updated 2026-10-17
Browser Use Bench v2.1 · medium · Updated 2026-10-17
Browser Use Bench v2.1 · high · Updated 2026-10-17
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.
- Reasoning effort
- medium · high
- Score
- Browser Use Bench v2.1 reports mean weighted rubric scores (0–100) over 180 browser tasks, not strict task completion rates. Each row keeps the model and reasoning effort separate. Cost per task is in USD; median time is the reported task-duration median. Evaluation methodology ↗
- Cost / task
- Average cost per task (USD)
- Median time
- Median task duration (min / s)