Artificial Analysis

Artificial Analysis Terminal-Bench v2.1

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

In index
Agentic
Best in agentic
Source ↗

Models21

Top result91.4%Claude Fable 5.1

Top-3 spread3.0 pts

Year2026

Result and price

20 of 21 results

Results

21 results

#ModelResult

01Claude Fable 5.191.4%

02Claude Opus 589.1%

03GPT-6 Astra88.4%

03Grok 4.688.4%

05GPT-5.6 Terra88.0%

06Gemini 3.8 Flash87.6%

07Qwen3.8-Flash-Next86.1%

08Gemini 3.7 Flash85.8%

09Kimi K385.0%

10Claude Fable 584.6%

10Claude Opus 4.884.6%

12GPT-5.584.3%

12GLM-5.3-Flash84.3%

14GLM-5.383.9%

15Claude Opus 4.7 (Adaptive)83.1%

16Grok 4.581.6%

17Inkling 2 Small81.3%

18GPT-5.6 Luna80.9%

19Claude Sonnet 580.5%

20Muse Spark 1.280.1%

21Qwen3.8-27B79.8%