Key Takeaways
Llama 4 Maverick wins:
- Cheaper input tokens
- Cheaper output tokens
- Larger context window
- Faster response time
- Better at math
Qwen3.5 397B A17B wins:
- Higher intelligence benchmark
- Better at coding
Price Advantage
Llama 4 Maverick
Benchmark Advantage
Qwen3.5 397B A17B
Context Window
Llama 4 Maverick
Speed
Llama 4 Maverick
Pricing Comparison
Price Comparison
| Metric | Llama 4 Maverick | Qwen3.5 397B A17B | Winner |
|---|---|---|---|
| Input (per 1M tokens) | $0.15 | $0.39 | Llama 4 Maverick |
| Output (per 1M tokens) | $0.60 | $0.90 | Llama 4 Maverick |
| Cache Read (per 1M) | N/A | $0.45 | Qwen3.5 397B A17B |
Using a 3:1 input/output ratio, Llama 4 Maverick is 49% cheaper overall.
Llama 4 Maverick Providers
No provider data available
Qwen3.5 397B A17B Providers
No provider data available
Benchmark Comparison
8
Benchmarks Compared
0
Llama 4 Maverick Wins
3
Qwen3.5 397B A17B Wins
Benchmark Scores
| Benchmark | Llama 4 Maverick | Qwen3.5 397B A17B | Winner |
|---|---|---|---|
Intelligence Index Overall intelligence score | 18.4 | 40.1 | |
Coding Index Code generation & understanding | 15.6 | 37.4 | |
Math Index Mathematical reasoning | 19.3 | - | - |
MMLU Pro Academic knowledge | 80.9 | - | - |
GPQA Graduate-level science | 67.1 | 86.1 | |
LiveCodeBench Competitive programming | 39.7 | - | - |
Aider Real-world code editing | 15.6 | - | - |
AIME Competition math | 39.0 | - | - |
Qwen3.5 397B A17B significantly outperforms in coding benchmarks.
Cost vs Quality
X-axis:
Y-axis:
Loading chart...
Llama 4 Maverick
Other models
Context & Performance
Context Window
Llama 4 Maverick
1,048,576
tokens
Qwen3.5 397B A17B
262,144
tokens
Llama 4 Maverick has a 75% larger context window.
Speed Performance
| Metric | Llama 4 Maverick | Qwen3.5 397B A17B | Winner |
|---|---|---|---|
| Tokens/second | 129.9 tok/s | 55.5 tok/s | |
| Time to First Token | 0.47s | 1.55s |
Llama 4 Maverick responds 134% faster on average.
Capabilities
Feature Comparison
| Feature | Llama 4 Maverick | Qwen3.5 397B A17B |
|---|---|---|
| Vision (Image Input) | ||
| Tool/Function Calls | ||
| Reasoning Mode | ||
| Audio Input | ||
| Audio Output | ||
| PDF Input | ||
| Prompt Caching | ||
| Web Search |
License & Release
| Property | Llama 4 Maverick | Qwen3.5 397B A17B |
|---|---|---|
| License | Open Source | Open Source |
| Author | Meta-llama | Qwen |
| Released | Apr 2025 | Feb 2026 |
Llama 4 Maverick Modalities
Input
textimage
Output
text
Qwen3.5 397B A17B Modalities
Input
textimagevideo
Output
text