Skip to main content

Artificial Analysis Terminal-Bench v2.1 (AA Terminal-Bench 2.1)

An independently evaluated Terminal-Bench v2.1 result from Artificial Analysis.

Data verified

Benchmark score on AA Terminal-Bench 2.1 — July 9, 2026

BenchLM mirrors the published score view for AA Terminal-Bench 2.1. GPT-5.6 Sol leads the public snapshot at 88.0% , followed by GPT-5.6 Terra (88.0%) and Claude Opus 4.8 (84.6%). BenchLM does not use these results to rank models overall.

14 modelsCodingCurrentDisplay onlyUpdated July 9, 2026

The published AA Terminal-Bench 2.1 snapshot is tightly clustered at the top: GPT-5.6 Sol sits at 88.0%, while the third row is only 3.4 points behind. The broader top-10 spread is 13.5 points, so the benchmark still separates strong models even when the leaders cluster.

14 models have been evaluated on AA Terminal-Bench 2.1. The benchmark falls in the Coding category. This category carries a 20% weight in BenchLM.ai's overall scoring system. AA Terminal-Bench 2.1 is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About AA Terminal-Bench 2.1

Year

2026

Tasks

Terminal-based agent tasks

Format

Task success rate

Difficulty

Agentic software engineering

Stored separately from the core Terminal-Bench lane because Artificial Analysis controls the evaluation configuration.

BenchLM freshness & provenance

Version

AA Terminal-Bench 2.1 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Benchmark score table (14 models)

1
GPT-5.6 Solgpt-5-6-sol
88.0%
2
GPT-5.6 Terragpt-5-6-terra
88.0%
3
Claude Opus 4.8claude-opus-4-8
84.6%
4
GPT-5.5gpt-5-5
84.3%
5
Grok 4.5grok-4-5
81.6%
6
GPT-5.6 Lunagpt-5-6-luna
80.9%
7
Claude Sonnet 5claude-sonnet-5
80.5%
8
Gemini 3.5 Flashgemini-3-5-flash
78.7%
9
GLM-5.2glm-5-2
77.9%
10
Qwen3.7 Maxqwen3-7-max
74.5%
11
Gemini 3.1 Progemini-3-1-pro
73.8%
12
Kimi K2.6kimi-2-6
65.9%
13
MiniMax M3minimax-m3
65.2%
14
MiMo-V2.5-Promimo-v2-5-pro
65.2%

FAQ

What does AA Terminal-Bench 2.1 measure?

An independently evaluated Terminal-Bench v2.1 result from Artificial Analysis.

Which model scores highest on AA Terminal-Bench 2.1?

GPT-5.6 Sol by OpenAI currently leads with a score of 88.0% on AA Terminal-Bench 2.1.

How many models are evaluated on AA Terminal-Bench 2.1?

14 AI models have been evaluated on AA Terminal-Bench 2.1 on BenchLM.

Last updated: July 9, 2026 · BenchLM version AA Terminal-Bench 2.1 2026

The AI models change fast. We track them for you.

For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.