Key Takeaways
GPT-5.1-Codex wins:
- Larger context window
- Faster response time
- Higher intelligence benchmark
- Better at coding
- Better at math
- Supports vision
- Supports tool calls
Qwen3 Max Thinking wins:
- Cheaper input tokens
- Cheaper output tokens
Price Advantage
Qwen3 Max Thinking
Benchmark Advantage
GPT-5.1-Codex
Context Window
GPT-5.1-Codex
Speed
GPT-5.1-Codex
Pricing Comparison
Price Comparison
| Metric | GPT-5.1-Codex | Qwen3 Max Thinking | Winner |
|---|---|---|---|
| Input (per 1M tokens) | $1.25 | $1.20 | Qwen3 Max Thinking |
| Output (per 1M tokens) | $10.00 | $6.00 | Qwen3 Max Thinking |
| Cache Read (per 1M) | $125000.00 | N/A | GPT-5.1-Codex |
Using a 3:1 input/output ratio, Qwen3 Max Thinking is 30% cheaper overall.
GPT-5.1-Codex Providers
OpenAI $1.25 (Cheapest)
Azure $1.25 (Cheapest)
Qwen3 Max Thinking Providers
Alibaba $1.20 (Cheapest)
Benchmark Comparison
6
Benchmarks Compared
0
GPT-5.1-Codex Wins
0
Qwen3 Max Thinking Wins
Benchmark Scores
| Benchmark | GPT-5.1-Codex | Qwen3 Max Thinking | Winner |
|---|---|---|---|
Intelligence Index Overall intelligence score | 42.2 | - | - |
Coding Index Code generation & understanding | 36.6 | - | - |
Math Index Mathematical reasoning | 95.7 | - | - |
MMLU Pro Academic knowledge | 86.0 | - | - |
GPQA Graduate-level science | 86.0 | - | - |
LiveCodeBench Competitive programming | 84.9 | - | - |
GPT-5.1-Codex significantly outperforms in coding benchmarks.
Cost vs Quality
X-axis:
Y-axis:
Loading chart...
GPT-5.1-Codex
Other models
Context & Performance
Context Window
GPT-5.1-Codex
400,000
tokens
Max output: 128,000 tokens
Qwen3 Max Thinking
262,144
tokens
Max output: 65,536 tokens
GPT-5.1-Codex has a 34% larger context window.
Speed Performance
| Metric | GPT-5.1-Codex | Qwen3 Max Thinking | Winner |
|---|---|---|---|
| Tokens/second | 166.3 tok/s | N/A | |
| Time to First Token | 15.87s | N/A |
Capabilities
Feature Comparison
| Feature | GPT-5.1-Codex | Qwen3 Max Thinking |
|---|---|---|
| Vision (Image Input) | ||
| Tool/Function Calls | ||
| Reasoning Mode | ||
| Audio Input | ||
| Audio Output | ||
| PDF Input | ||
| Prompt Caching | ||
| Web Search |
License & Release
| Property | GPT-5.1-Codex | Qwen3 Max Thinking |
|---|---|---|
| License | Proprietary | Proprietary |
| Author | OpenAI | Qwen |
| Released | Nov 2025 | Feb 2026 |
GPT-5.1-Codex Modalities
Input
textimage
Output
text
Qwen3 Max Thinking Modalities
Input
text
Output
text