← Claude Opus 4.8 · API · High effort (default)
Evidenceacceptedindependent_lab
Terminal-Bench
Artificial Analysis — Terminal-Bench 2.1 (Opus 4.8 max)
ev_2026_07_opus48_terminal
Result
84.64%
Confidence A
- Tested
- 2026-05-28
- Runs
- 1
Configuration
How it was measured
- Exact model
- claude-opus-4-8
- Reasoning
- max
- Agent harness
- Terminus-2 / AA Terminal-Bench 2.1
- Tool access
- terminal agent tools
- Prompting
- AA standard
Caveats
Known limitations
- Max effort config.
Weighting
Evidence weight factors
The engine weights each evidence row by these factors (0–1) when fusing scores — higher is more trusted.
relevance0.90
quality1.00
recency0.95
health0.90
comparability0.85
reliability0.85
Benchmark
Terminal-Bench
Agentic terminal / tool-use suite measuring multi-step shell and environment task completion (Terminus-2 harness commonly cited).
Benchmark source →