LLM Stats (Terminal-Bench-Science 0.1): leaderboard

Terminal-Bench-Science 0.1 as listed by LLM Stats: 70 expert-authored scientific research workflows across the life, physical, earth, mathematical and engineering sciences, completed by agents in terminal environments. Score in percent; higher is better.

Metric: Score (%). Source: llm-stats.com. Saturation forecast: Around February 2027. 12 models tracked. Updated 13 Nov 2026.

Top models

#ModelScoreOverall rank
1Claude Mythos 5.275.3
2Claude Fable 5.274.6#1
3GPT-6 Astra64.6#6
4Claude Sonnet 5.559.9#19
5Claude Opus 5.558.7#5
6GPT-6.1 Terra58.3#21
7Gemini 4 Argon57.6#12
8GPT-6.1 Sol57.02#10
9Claude Fable 5.152.6#15
10Kimi K3.1 Pro38.1#29
11ERNIE 5.5 Flash Preview21#98
12Claude Haiku 5.520.6#70

No result here: #2 Gemini 4 Carbon.

Interactive version: theaggregate.ai/benchmark?slug=llm-stats-terminal-bench-science-0-1 · How It Works · Data refreshed daily, snapshot 2026-11-16.