Atlas

Benchmarks

← All benchmarks

SAGE - Linear Algebra

Math · 2025-10-08

The Linear Algebra split of SAGE. This child benchmark separates a source-reported subtask or subtrack from the parent aggregate so scores at different grains do not share one benchmark_slug.

Top models (higher is better)

ModelScore
Opus 4.878.3
Opus 4.777.0
Claude Opus 576.1
Opus 4.675.4
GPT-5.574.4
Gemini 3.1 Pro Preview74.2
Kimi K372.7
Gemma 4 31B IT72.6
Claude Fable 571.5
GPT-5.4 Mini71.5
Gemini 3 Flash Preview71.0
Kimi K2.571.0
Opus 4.570.6
GPT-5.6 Sol70.4
Gemini 3.6 Flash69.9
GPT-5.269.6
Sonnet 569.0
Muse Spark 1.168.9
GPT-5.468.8
GPT-5.168.6
Gemini 3.5 Flash68.3
Kimi K2.668.1
MiniMax M366.8
Gemini 3 Pro Preview65.1
GPT-5.6 Terra64.0
Llama 4 Maverick Instruct63.9
Gemini 3.5 Flash-Lite63.7
GPT-5.6 Luna63.2
Sonnet 4.663.2
GPT-5 Mini62.7
GPT-561.6
o361.4
Llama 4 Scout Instruct61.2
GPT-5.4 Nano60.7
Qwen3.6 Plus (2026-04-02)60.0
Qwen3.6 27B59.7
Gemini 3.1 Flash-Lite Preview58.9
MiMo-V2.558.8
Gemini 2.5 Flash58.5
Gemini 2.5 Flash Preview (09-2025)57.3
Loading Atlas data…