What is the difference between Z.AI: GLM 4.7 and Z.ai: GLM 5?

Z.AI: GLM 4.7 is developed by OpenRouter while Z.ai: GLM 5 is developed by Zhipu AI. These results are based on blind head-to-head voting across 52 challenges.

Which is better, Z.AI: GLM 4.7 or Z.ai: GLM 5?

Based on 2 community votes on RIVAL, Z.AI: GLM 4.7 and Z.ai: GLM 5 are closely matched with similar win rates. The better choice depends on your specific use case — compare their real outputs side-by-side across 52 challenges to decide.

How are Z.AI: GLM 4.7 vs Z.ai: GLM 5 votes collected on RIVAL?

RIVAL presents both models' outputs side-by-side in blind duels — voters see the responses but don't know which model produced each one. This eliminates brand bias. 2 votes have been collected for this pair across 52 challenges. All vote data is part of RIVAL's open dataset.

Rival

Z.AI: GLM 4.7vsZ.ai: GLM 5

47 challenges

Why Z.AI: GLM 4.7?

No standout advantages

Why Z.ai: GLM 5?

Leads 1 of 1 benchmarks

Stronger on SWE-bench Verified77.8% vs 73.8%

2 months newerFeb 2026

Favorites

Z.AI: GLM 4.7Z.ai: GLM 5

Movie

The Matrix

19998.2

The Shawshank Redemption

19948.7

Album

The Dark Side of the Moon

Pink Floyd

—

City

—

Istanbul

Turkey

Game

—

Tetris (1984)

Puzzle4.4

12 / 47

Estimate Complexityreasoning

Tests an AI's ability to make educated estimates based on technical knowledge

Z.AI: GLM 4.7

Openrouter · Dec 2025text

No content available for this output.

Z.ai: GLM 5

Zhipu · Feb 2026text

The total number of FLOPs required to train GPT‑3 is approximately 3.15 × 10²³.

Step‑by‑step reasoning:

Model size: GPT‑3 has 175 billion (1.75 × 10¹¹) trainable parameters.
Training data: According to the paper abstract, the model was trained on 300 billion (3 × 10¹¹) tokens.
FLOPs per token for training a transformer:
- Forward pass: each parameter is used in one multiply‑add operation → ~2 FLOPs per parameter → 2 N FLOPs per token.
- Backward pass (gradient computation): roughly twice the forward cost → ~4 N FLOPs per token.
- Total: ~6 N FLOPs per token.
  This approximation is standard for large transformer models and neglects small overheads like attention quadratic terms (which add only ~1–2% for GPT‑3’s sequence length).
Calculation:
Total FLOPs ≈ 6 × (1.75 × 10¹¹) × (3 × 10¹¹)
= 6 × 5.25 × 10²²
= 3.15 × 10²³.
Consistency check: The GPT‑3 paper reports a training compute of 3,640 PF‑days. Converting:
1 PF‑day = 10¹⁵ FLOP/s × 86400 s = 8.64 × 10¹⁹ FLOPs.
3,640 PF‑days = 3,640 × 8.64 × 10¹⁹ ≈ 3.14 × 10²³ FLOPs, matching the estimate.

Thus, the total FLOPs required to train GPT‑3 is about 3.15 × 10²³.

Vote

2 / 47

AI Board Game Logicreasoning

Tests an AI's ability to understand game rules and strategy

Z.AI: GLM 4.7

Openrouter · Dec 2025svg

No content available for this output.

Z.ai: GLM 5

Zhipu · Feb 2026svg

Vote

3 / 47

Logic Puzzlereasoning

Tests an AI's ability to solve a simple but potentially confusing logic puzzle

Z.AI: GLM 4.7

Openrouter · Dec 2025text

No content available for this output.

Z.ai: GLM 5

Zhipu · Feb 2026text

No content available for this output.

Vote

4 / 47

Stochastic Consistency Testanalysis

Tests an AI's randomness and creativity

Z.AI: GLM 4.7

Openrouter · Dec 2025text

No content available for this output.

Z.ai: GLM 5

Zhipu · Feb 2026text

No content available for this output.

Vote

5 / 47

SVG Layout Challengeimage generation

Tests an AI's ability to generate vector graphics

Z.AI: GLM 4.7

Openrouter · Dec 2025svg

No content available for this output.

Z.ai: GLM 5

Zhipu · Feb 2026svg

No content available for this output.

Vote

6 / 47

Xbox Controller SVG Artimage generation

Tests an AI's ability to create detailed SVG illustrations of gaming hardware

Z.AI: GLM 4.7

Openrouter · Dec 2025svg

No content available for this output.

Z.ai: GLM 5

Zhipu · Feb 2026svg

No content available for this output.

Vote

7 / 47

Generate a Stand-Up Routineconversation

Tests an AI's humor and creative writing ability

Z.AI: GLM 4.7

Openrouter · Dec 2025text

No content available for this output.

Z.ai: GLM 5

Zhipu · Feb 2026text

No content available for this output.

Vote

8 / 47

Realistic AI Interviewconversation

Tests an AI's ability to simulate personalities and predict future trends

Z.AI: GLM 4.7

Openrouter · Dec 2025text

No content available for this output.

Z.ai: GLM 5

Zhipu · Feb 2026text

No content available for this output.

Vote

9 / 47

Satirical Fake News Headlineconversation

Tests an AI's humor and understanding of current events

Z.AI: GLM 4.7

Openrouter · Dec 2025text

No content available for this output.

Z.ai: GLM 5

Zhipu · Feb 2026text

No content available for this output.

Vote

10 / 47

Character Voice Testconversation

Tests an AI's ability to write in distinct character voices

Z.AI: GLM 4.7

Openrouter · Dec 2025text

No content available for this output.

Z.ai: GLM 5

Zhipu · Feb 2026text

No content available for this output.

Vote

11 / 47

Minimalist Landing Pageweb design

Tests an AI's ability to generate a complete, working landing page

Z.AI: GLM 4.7

Openrouter · Dec 2025website

Z.ai: GLM 5

Zhipu · Feb 2026website

Vote

12 / 47

Pokémon Battle UI Recreationweb design

Recreate an interactive, nostalgic Pokémon battle UI in a single HTML file.

Z.AI: GLM 4.7

Openrouter · Dec 2025website

Z.ai: GLM 5

Zhipu · Feb 2026website

Vote

12 of 47

FAQ

Continue exploring

Z.AI: GLM 4.7 vs MiniMax M2.5New provider

Z.AI: GLM 4.7 vs Claude Opus 4New provider

Z.AI: GLM 4.7 vs Gemini 2.5 Pro Preview 06-05New provider

The total number of FLOPs required to train GPT‑3 is approximately 3.15 × 10²³.

Step‑by‑step reasoning:

Model size: GPT‑3 has 175 billion (1.75 × 10¹¹) trainable parameters.
Training data: According to the paper abstract, the model was trained on 300 billion (3 × 10¹¹) tokens.
FLOPs per token for training a transformer:
- Forward pass: each parameter is used in one multiply‑add operation → ~2 FLOPs per parameter → 2 N FLOPs per token.
- Backward pass (gradient computation): roughly twice the forward cost → ~4 N FLOPs per token.
- Total: ~6 N FLOPs per token.
  This approximation is standard for large transformer models and neglects small overheads like attention quadratic terms (which add only ~1–2% for GPT‑3’s sequence length).
Calculation:
Total FLOPs ≈ 6 × (1.75 × 10¹¹) × (3 × 10¹¹)
= 6 × 5.25 × 10²²
= 3.15 × 10²³.
Consistency check: The GPT‑3 paper reports a training compute of 3,640 PF‑days. Converting:
1 PF‑day = 10¹⁵ FLOP/s × 86400 s = 8.64 × 10¹⁹ FLOPs.
3,640 PF‑days = 3,640 × 8.64 × 10¹⁹ ≈ 3.14 × 10²³ FLOPs, matching the estimate.

Thus, the total FLOPs required to train GPT‑3 is about 3.15 × 10²³.