Inference
Artificial Analysis

Artificial Analysis Terminal-Bench v4.0

An independently evaluated Terminal-Bench v4.0 result from Artificial Analysis, one of the ten components of its Intelligence Index v4.3.

ModelsModels with a result.23
Top resultBest result on this test.63.6%Claude Sonnet 5.5
Top-3 spreadPoints from first to third.4.5 pts
YearYear of release.2026

Result and price

020406080100$0.3$1$3$10$30$100RESULTOUTPUT PRICE PER 1M TOKENS · LOG SCALE

Results

23 results
#ModelResultThe score from the source.
01Claude Sonnet 5.563.6%
02Claude Opus 5.559.6%
03GPT-6 Astra59.1%
04Gemini 4 Argon57.1%
05GPT-6.1 Sol56.1%
06Claude Fable 5.152.0%
07GPT-6 Sol43.9%
08GLM-5.341.9%
09MiMo-V2.6-Pro34.8%
10Muse Spark 1.333.3%
10Step 5 Preview33.3%
12GLM-5.3-Flash32.8%
13DeepSeek V4.1 Flash26.8%
13Mistral Large 426.8%
15Grok 4.725.8%
16Gemini 3.8 Flash19.7%
17Kimi K312.6%
17GPT-6 Luna12.6%
19Qwen3.8-27B5.6%
20MiniMax M32.0%
21Inkling1.0%
22Muse Glimmer 30B0.5%
22Nemotron 3 Ultra0.5%