Domains: CodingCyberScience
Skills: CodingAgenticTool UseReasoningInstruction Following

Four-Factor Integrity Breakdown & Primary-Source Evidence

Privacy

Weight 40%
0/10
Access Model: Public Plaintext
"The 4.0 release of Terminal-Bench, developed by Stanford University researchers, the Laude Institute, and the open source community. Covers software engineering, system administration, data processing, model training, and security, with each task graded by its own verification suite."

Originality

Weight 25%
10/10
Reuse Profile: All Original (0% reuse)
"Today we are releasing the first version of Terminal-Bench, a benchmark to quantify how well AI agents perform complex tasks in the terminal."

Freshness

Weight 20%
7/10
Initial Release: 2025-05Latest Refresh: 2026-08Rolling Updates: No
"Replaced Terminal-Bench 2.1 with Terminal-Bench 4.0 (66 tasks, mini-swe-agent harness)"

Grading

Weight 15%
3.3/10
Integrity: Self-Reported / Live NetworkSandbox: live internet
"Terminal-Bench is an open-internet benchmark. We want agents to have their full capabilities available, so disabling network access is not a valid way to make a task difficult."
Primary source (GitHub) ↗ Verified 2026-11-17

Frontier Model Standings on Terminal-Bench 4.0

Top 15 active models tracked
Rank Model Official Score Percentile
#1Kimi K3.1 Pro max Kimi67.2%100.0p
#2Gemini 4 Carbon high Google65.1%98.0p
#3GPT-6.2 Astra max OpenAI64.1%95.9p
#4Claude Sonnet 5.5 max Anthropic63.6%92.9p
#4Gemini 4 Neon xhigh Google63.6%92.9p
#6GPT-6.2 Sol max OpenAI60.1%89.8p
#7Claude Fable 5.2 max Anthropic59.6%86.7p
#7Claude Opus 5.5 max Anthropic59.6%86.7p
#9GPT-6 Astra max OpenAI59.1%83.7p
#10Gemini 4 Argon high Google57.1%80.6p
#10Muse Wonder Full max Meta57.1%80.6p
#12GPT-6.1 Sol max OpenAI56.1%77.6p
#13GPT-6.1 Terra max OpenAI55.6%75.5p
#14Gemini 4 Hydrogen xhigh Google53.5%73.5p
#15Claude Fable 5.1 max Anthropic52.0%70.4p

Embeddable Audit Badge

View Markdown (.md)

Benchmark maintainers can embed this live SVG badge in GitHub READMEs or documentation:

BenchAudit Terminal-Bench 4.0 Tier C 4.4/10
[![BenchAudit Tier C](https://benchaudit.org/badges/terminal-bench-4-0.svg)](https://benchaudit.org/benchmarks/terminal-bench-4-0/)