SmophyAI

Published daily · Next update 02:00 UTC

Real data comparison

Z.ai: GLM 5.2 (batch) vs Tencent: Hy3 preview

On quality, Z.ai: GLM 5.2 (batch) leads (52.6 vs 42.2). On price, Tencent: Hy3 preview is cheaper ($0.10 vs $0.11 per 1M). In real production usage, Z.ai: GLM 5.2 (batch) is used more (rank #4 vs #8 of 291).

  • Z.ai: GLM 5.2 (batch)
  • Tencent: Hy3 preview
Quality (Intelligence Index)52.6 / 42.2
Price ($/1M blended)$0.11 / $0.10
Average usage share5.54% / 2.60%
Coding index68.8 / 58.8
Agentic index45.7 / 31.4
Context window1,048,576 / 262,144
Quality per dollar489.3 pts/$ / 423.1 pts/$

Usage share over time

8.48%6.36%4.24%2.12%0.00%Share of usageJul 5Jul 22Aug 8
  • Z.ai: GLM 5.2 (batch)
  • Tencent: Hy3 preview

Frequently asked questions

Z.ai: GLM 5.2 (batch) vs Tencent: Hy3 preview: which is better quality?

Z.ai: GLM 5.2 (batch) scores higher on Artificial Analysis's Intelligence Index (52.6 vs 42.2).

Z.ai: GLM 5.2 (batch) vs Tencent: Hy3 preview: which is cheaper?

Tencent: Hy3 preview is cheaper at $0.10/1M vs $0.11/1M.

Z.ai: GLM 5.2 (batch) vs Tencent: Hy3 preview: which is used more?

Z.ai: GLM 5.2 (batch) has higher real OpenRouter usage share (rank #4 vs #8 of 291).

Source: OpenRouter (openrouter.ai/rankings), as of August 9, 2026.

Benchmark scores: Artificial Analysis (artificialanalysis.ai) via OpenRouter (openrouter.ai/rankings).

Methodology: smophy.ai/benchmark/methodology

Token counts originate from each provider's own tokenizer and are not directly comparable across providers.