Model Comparison
Qwen2 Instruct 72B
vs. Qwen3.5 122B A10B (Non-reasoning)
Comparing 2 AI models · 11 benchmarks · Alibaba
Recommended Pick
Al Qwen3.5 122B A10B (Non-reasoning) 6 metric wins Strongest on: Throughput, Reasoning, Intelligence
Lowest Price
Qwen2 Instruct 72B
$0.00/1M input price
Best Reasoning
Qwen3.5 122B A10B (Non-reasoning)
44.5 reasoning score
Blends available reasoning benchmarks
Best for Coding
Qwen3.5 122B A10B (Non-reasoning)
31.6 coding index
Composite Indices
Higher is better; speed and price are normalized
Standard Benchmarks
Only benchmarks with data are shown
Differences That Matter
Price gap
Qwen2 Instruct 72B is ∞x cheaper on input tokens than Qwen3.5 122B A10B (Non-reasoning).
Reasoning gap
Qwen3.5 122B A10B (Non-reasoning) leads Qwen2 Instruct 72B by 17.0 points on reasoning.
Top-pick rationale
Qwen3.5 122B A10B (Non-reasoning) wins 6 measurable categories, including Throughput, Reasoning, Intelligence, GPQA.
Response Face-Off
Run one prompt through the selected models and compare response quality with live speed and cost context.
Qwen2 Instruct 72B
Alibaba
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Qwen3.5 122B A10B (Non-reasoning)
Alibaba
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Full Comparison
| Metric | Al Qwen2 Instruct 72B | Top Pick Al Qwen3.5 122B A10B (Non-reasoning) |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $0.00/1M | $0.40/1M |
| Output Cost | $0.00/1M | $3.20/1M |
| Blended (3:1) | — | $1.10/1M |
| Specifications | ||
| Organization | Alibaba | Alibaba |
| Release Date | Jun 7, 2024 | Feb 24, 2026 |
| Performance & Speed | ||
| Throughput | — | 163.3 tok/s |
| TTFT | — | 1080ms |
| Latency | — | 1080ms |
| Composite Indices | ||
| Value Score | — | 100.0 |
| Reasoning Score | 27.5 | 44.5 |
| Intelligence | 11.7 | 35.9 |
| Coding | — | 31.6 |
| Standard Benchmarks | ||
| GPQA | 37.1% | 82.7% |
| MMLU Pro | 62.2% | — |
| HLE | 3.7% | 14.8% |
| LiveCodeBench | 15.9% | — |
| MATH 500 | 70.1% | — |
| AIME (Original) | 14.7% | — |
| SciCode | 22.9% | 35.6% |
| LCR | — | 56.0% |
| IFBench | — | 50.8% |
| TAU-bench v2 | — | 84.5% |
| TerminalBench Hard | — | 29.5% |
Key Takeaways
Qwen2 Instruct 72B offers the best value at $0.00/1M, making it ideal for high-volume applications and cost-conscious projects.
Qwen3.5 122B A10B (Non-reasoning) has the strongest reasoning profile with a 44.5 reasoning score, combining the available reasoning-heavy benchmarks.
Qwen3.5 122B A10B (Non-reasoning) reaches a 31.6 coding index, making it the top choice for software development and code generation tasks.
All models support context windows of ∞+ tokens, suitable for processing lengthy documents and maintaining extended conversations.
When to Choose Each Model
Qwen2 Instruct 72B
- Cost-sensitive applications
- High-volume processing
Qwen3.5 122B A10B (Non-reasoning)
- Complex reasoning tasks
- Research & analysis
- Code generation
- Software development
