Atlas

Benchmarks

← All benchmarks

HLAB-Vals-1.1 - Criteria Pass Rate - Environmental ESG

Professional Work · 2026-10-19

Criteria pass rate (judge-averaged, Harvey's definition) on the Environmental ESG practice-area tasks of HLAB-Vals-1.1, distinct from that area's task pass rate.

Top models (higher is better)

ModelScore
Gemini 4 Argon97.3
Muse Wonder94.8
Muse Spark Open93.7
Muse Wonder Full93.2
DeepSeek V4.1 Flash 101793.0
Gemini 3.8 Flash92.5
GLM-5.3 Flash91.9
GLM-5.391.9
Grok 4.791.0
Mistral Large 4 Preview91.0
MiMo-V2.6-Flash90.5
DeepSeek V4 Pro 081389.8
Kimi K389.8
GPT-6 Astra89.6
MiMo-V2.6-Pro89.4
MiniMax M3.1 Flash89.4
Claude Sonnet 5.588.9
Claude Haiku 5.588.4
GPT-6.1 Sol88.2
Beam 1.0 501B A23B88.0
GPT-6 Luna87.6
Hy4 Preview86.6
Claude Opus 5.586.2
Mercury 385.3
Inkling84.8
Inkling-Small76.2
Loading Atlas data…