AIThe Decoderabout 6 hours ago
Snowflake CEO: GLM-5.2 rivals Opus 4.7 at lower cost
1 min read
Snowflake benchmarked GLM-5.2 against Opus 4.7 across 103 coding tasks. The models solved 66% and 67% of tasks respectively. Opus achieved 53.7% first-attempt accuracy versus GLM's 47.6%. GLM used 860 million tokens to Opus's 439 million. GLM costs $1.40 per million input tokens versus Opus's $5.
Level
Hype check
Tap to vote and see what everyone thinks.
