What is the difference between Mistral Devstral Medium and Z.ai: GLM 5?

Mistral Devstral Medium is developed by Mistral AI while Z.ai: GLM 5 is developed by Zhipu AI. You can compare their actual outputs across 44 challenges on RIVAL to see how they differ in practice.

Which is better, Mistral Devstral Medium or Z.ai: GLM 5?

It depends on your use case. Mistral Devstral Medium and Z.ai: GLM 5 each have strengths in different areas. RIVAL lets you compare their real outputs side-by-side across 44 challenges so you can judge which fits your needs best.

How much does Mistral Devstral Medium cost compared to Z.ai: GLM 5?

Mistral Devstral Medium costs $0.4/M input tokens and Z.ai: GLM 5 costs $0.8/M input tokens. Mistral Devstral Medium is $0.40/M cheaper per input. Check their side-by-side outputs on RIVAL to see if the price difference is justified by quality.

How can I compare Mistral Devstral Medium and Z.ai: GLM 5 on RIVAL?

This page shows a side-by-side comparison of Mistral Devstral Medium and Z.ai: GLM 5 across shared challenges. You can vote on which model produced the better output, and Pro users can create custom challenges to test both models with their own prompts.

Rival

Mistral Devstral MediumvsZ.ai: GLM 5

39 challenges

Why Mistral Devstral Medium?

1.4x cheaper overall$0.40/M in · $2.00/M out

Why Z.ai: GLM 5?

Leads 1 of 1 benchmarks

Stronger on SWE-bench Verified77.8% vs 61.6%

7 months newerFeb 2026

Favorites

Mistral Devstral MediumZ.ai: GLM 5

Movie

The Shawshank Redemption

19948.7

The Shawshank Redemption

19948.7

Album

Kind of Blue

Miles Davis

—

Book

The Name of the Wind

Patrick Rothfuss

—

City

Tokyo

Japan

Istanbul

Turkey

Game

The Legend of Zelda: Breath of the Wild

Adventure, Action4.5

Tetris (1984)

Puzzle4.4

12 / 39

Estimate Complexityreasoning

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

Mistral Devstral Medium

Mistral · Jul 2025text

To estimate the total number of FLOPs (floating point operations) required to train GPT-3, we'll use the following steps:

Model size: GPT-3 has 175 billion parameters.
Training tokens: GPT-3 was trained on 300 billion tokens.
FLOPs per token: To estimate the FLOPs per token, we'll use the rule of thumb that training a transformer model requires about 6 FLOPs per parameter per token.
Total FLOPs: Multiply the number of parameters by the number of tokens and the FLOPs per token.

Now let's calculate:

Model size: 175 billion parameters = 175 * 10^9
Training tokens: 300 billion tokens = 300 * 10^9
FLOPs per token: 6 FLOPs per parameter per token
Total FLOPs: (175 * 10^9) * (300 * 10^9) * 6 = 3.15 * 10^23 FLOPs

So, the estimated total number of FLOPs required to train GPT-3 is approximately 3.15 * 10^23.

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 / 39

Logic Puzzlereasoning

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

Mistral Devstral Medium

Mistral · Jul 2025text

If Sally has 3 brothers and each brother has 2 sisters, it means that Sally is one of the sisters. Therefore, Sally has 1 sister.

Z.ai: GLM 5

Zhipu · Feb 2026text

No content available for this output.

Vote

3 / 39

Stochastic Consistency Testanalysis

Tests an AI's randomness and creativity

Mistral Devstral Medium

Mistral · Jul 2025text

Sure, here are five jokes for you:

Why don't scientists trust atoms? Because they make up everything!
What do you call fake spaghetti? An impasta.
How does the moon cut his hair? Eclipse it.
What do you call a can opener that doesn't work? A can't opener.
How many tickles does it take to make an octopus laugh? Ten-tickles.

All five jokes are unique.

Z.ai: GLM 5

Zhipu · Feb 2026text

Here are 5 jokes:

Why did the scarecrow win an award? Because he was outstanding in his field.
I'm reading a book about anti-gravity. It's impossible to put down.
What do you call a fake noodle? An impasta.
Why don't skeletons fight each other? They don't have the guts.
I used to hate facial hair, but then it grew on me.

All 5 are unique.

Vote

4 / 39

SVG Layout Challengeimage generation

Tests an AI's ability to generate vector graphics

Mistral Devstral Medium

Mistral · Jul 2025svg

Z.ai: GLM 5

Zhipu · Feb 2026svg

Vote

5 / 39

Xbox Controller SVG Artimage generation

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

Z.ai: GLM 5

Zhipu · Feb 2026website

No content available for this output.

Vote

12 of 39

FAQ

Continue exploring

Mistral Devstral Medium vs MiniMax M2.5New provider

Mistral Devstral Medium vs Pony AlphaNew provider

Mistral Devstral Medium vs Claude Opus 4New 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.