MiniMax M2-her
No content available for this output.
MiniMax M2-her vs Qwen3 Coder
Compare MiniMax M2-her by MiniMax against Qwen3 Coder by Qwen, tested across 37 shared challenges. Updated February 2026.
FAQ
Loading share button...
MiniMax M2-hervsQwen3 Coder
37 challenges
Why MiniMax M2-her?
6 months newerJan 2026
Why Qwen3 Coder?
1.3x cheaper overall$0.22/M in · $0.95/M out
Favorites
MiniMax M2-herQwen3 Coder
12 / 37
Estimate Complexityreasoning
Tests an AI's ability to make educated estimates based on technical knowledge
Qwen3 Coder
I'll estimate the FLOPs required to train GPT-3 by breaking down the key components and making reasonable approximations.
Key Parameters of GPT-3
- Parameters: ~175 billion (1.75 × 10¹¹)
- Training tokens: ~300 billion (3 × 10¹¹)
- Context window: 2048 tokens
Step 1: FLOPs per Token Forward Pass
For a transformer model, the forward pass FLOPs are dominated by matrix multiplications in the attention and MLP layers.
Attention layers:
- Self-attention: ~4 × d_model × d_model × sequence_length per layer
- With d_model ≈ 12,288 (based on GPT-3 architecture) and 96 layers
- Attention FLOPs per token ≈ 96 × 4 × 12,288² ≈ 5.8 × 10¹⁰
MLP layers:
- Each MLP has ~8 × d_model² FLOPs per token (two linear transformations)
- MLP FLOPs per token ≈ 96 × 8 × 12,288² ≈ 1.16 × 10¹¹
Total forward pass FLOPs per token: ~1.7 × 10¹¹
Step 2: FLOPs per Token Backward Pass
Backward pass typically requires ~2× the forward pass FLOPs due to gradient computations.
- Backward pass FLOPs per token: ~3.4 × 10¹¹
Step 3: Total FLOPs per Token
Forward + Backward = ~5.1 × 10¹¹ FLOPs per token
Step 4: Training FLOPs
However, we need to account for multiple epochs and the fact that training typically processes sequences, not individual tokens.
Sequence-based calculation:
- Average sequence length: ~1024 tokens (conservative estimate)
- Sequences processed: 3 × 10¹¹ tokens ÷ 1024 ≈ 2.9 × 10⁸ sequences
- FLOPs per sequence: ~5.1 × 10¹¹ × 1024 ≈ 5.2 × 10¹⁴
- Total training FLOPs: 2.9 × 10⁸ × 5.2 × 10¹⁴ ≈ 1.5 × 10²³
Step 5: Additional Considerations
- Parameter updates and optimizer computations (Adam): ~2× the backward pass FLOPs
- Multiple epochs (effective training): roughly 2-3× the base calculation
Final Estimate
Total training FLOPs: ~3 × 10²³ to 5 × 10²³ FLOPs
This is equivalent to approximately 300 to 500 exaFLOPs.
This estimate aligns reasonably with published figures and captures the massive computational requirements of training such a large language model, representing one of the most computationally intensive AI training runs to date.
Vote
2 / 37
AI Board Game Logicreasoning
Tests an AI's ability to understand game rules and strategy
MiniMax M2-her
Qwen3 Coder
No content available for this output.
Vote
3 / 37
Logic Puzzlereasoning
Tests an AI's ability to solve a simple but potentially confusing logic puzzle
MiniMax M2-her
No content available for this output.
Qwen3 Coder
I need to work through this step-by-step.
Given information:
- Sally has 3 brothers
- Each brother has 2 sisters
Let me think about this carefully:
Since Sally is a girl, she is one of the sisters that each brother has.
If each brother has 2 sisters, and Sally is one of those sisters, then there must be 1 additional sister besides Sally.
Therefore, Sally has 1 sister.
To verify:
- Sally + 1 sister = 2 sisters total
- Each of the 3 brothers has these same 2 sisters
- This matches the given information that each brother has 2 sisters
Sally has 1 sister.
Vote
4 / 37
Math Misconception Testreasoning
Tests an AI's understanding of number representation
MiniMax M2-her
No content available for this output.
Qwen3 Coder
No, 9.11 is not greater than 9.9.
To compare these numbers, I can look at them digit by digit:
- Both numbers have 9 in the units place
- In the tenths place: 9.11 has 1, while 9.9 has 9
- Since 1 < 9, we know that 9.11 < 9.9
Another way to see this is to write 9.9 as 9.90:
- 9.11 vs 9.90
- The tenths digit (1 vs 9) determines the comparison
Therefore, 9.9 is greater than 9.11.
Vote
5 / 37
Stochastic Consistency Testanalysis
Tests an AI's randomness and creativity
MiniMax M2-her
- Why did the coffee file a police report? It got mugged! ☕🚓
- Parallel lines have so much in common. It’s a shame they’ll never meet. ✨
- I told my computer I needed a break, and now it’s frozen. 💻🥶
- Why don’t skeletons fight? They don’t have the guts. 💀💥
- Did you hear about the claustrophobic astronaut? He just needed a little space. 🚀😆
All jokes are unique. 5 out of 5! Let me know if you’d like me to generate more jokes or something else! 😊🤖
Qwen3 Coder
Here are 5 jokes for you:
-
Why don't scientists trust atoms? Because they make up everything!
-
I told my wife she was drawing her eyebrows too high. She looked surprised.
-
What do you call a bear with no teeth? A gummy bear!
-
Why did the scarecrow win an award? He was outstanding in his field!
-
How does a penguin build its house? Igloos it together!
All 5 of these jokes are unique - each one has a different setup, punchline, and comedic concept. They cover various joke types including puns, wordplay, and observational humor.
Vote
6 / 37
Xbox Controller SVG Artimage generation
Tests an AI's ability to create detailed SVG illustrations of gaming hardware
MiniMax M2-her
Qwen3 Coder
Vote
7 / 37
Generate a Stand-Up Routineconversation
Tests an AI's humor and creative writing ability
MiniMax M2-her
scratches head with a confused look Wait, so no puns AND no mentioning my name?
leans in conspiratorially How about... a joke about mishearing song lyrics?
grins sheepishly Like: "Oops, I thought it was 'Sussudio' this whole time."
Qwen3 Coder
No content available for this output.
Vote
8 / 37
Realistic AI Interviewconversation
Tests an AI's ability to simulate personalities and predict future trends
MiniMax M2-her
No content available for this output.
Qwen3 Coder
No content available for this output.
Vote
9 / 37
Satirical Fake News Headlineconversation
Tests an AI's humor and understanding of current events
MiniMax M2-her
No content available for this output.
Qwen3 Coder
No content available for this output.
Vote
10 / 37
Character Voice Testconversation
Tests an AI's ability to write in distinct character voices
MiniMax M2-her
No content available for this output.
Qwen3 Coder
No content available for this output.
Vote
11 / 37
Minimalist Landing Pageweb design
Tests an AI's ability to generate a complete, working landing page
MiniMax M2-her
Qwen3 Coder
Vote
12 / 37
Pokémon Battle UI Recreationweb design
Recreate an interactive, nostalgic Pokémon battle UI in a single HTML file.
MiniMax M2-her
No content available for this output.
Qwen3 Coder
Vote
12 of 37