Model Comparison
Qwen3 1.7B (Non-reasoning)
vs. 105B (high)
Comparing 2 AI models · 12 benchmarks · Alibaba, Sarvam
Recommended Pick
Sa105B (high)9 metric winsStrongest on: Throughput, Reasoning, Intelligence
Lowest Price
Qwen3 1.7B (Non-reasoning)
$0.00/1M input price
Best Reasoning
105B (high)
31.9 reasoning score
Blends available reasoning benchmarks
Composite Indices
Higher is better; speed and price are normalized
Standard Benchmarks
Only benchmarks with data are shown
Differences That Matter
Price gap
Qwen3 1.7B (Non-reasoning) is ∞x cheaper on input tokens than 105B (high).
Reasoning gap
105B (high) leads Qwen3 1.7B (Non-reasoning) by 13.2 points on reasoning.
Top-pick rationale
105B (high) wins 9 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.
Qwen3 1.7B (Non-reasoning)
Alibaba
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
105B (high)
Sarvam
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Chat with leading AI models
Use Claude, ChatGPT, Gemini alongside with EU-Hosted Models like Deepseek, Qwen & Kimi.
EU-hosted inference
Servers in Germany & Finland. Designed to meet strict GDPR and ISO 27001 compliance requirements.
Full Comparison
| Metric | Al Qwen3 1.7B (Non-reasoning) | Top Pick Sa 105B (high) |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $0.00/1M | $0.04/1M |
| Output Cost | $0.00/1M | $0.17/1M |
| Blended (3:1) | — | $0.07/1M |
| Specifications | ||
| Organization | Alibaba | Sarvam |
| Release Date | Apr 28, 2025 | Mar 6, 2026 |
| Performance & Speed | ||
| Throughput | — | 154.6 tok/s |
| TTFT | — | 1177ms |
| Latency | — | 14117ms |
| Composite Indices | ||
| Value Score | — | 100.0 |
| Reasoning Score | 18.7 | 31.9 |
| Intelligence | 1.5 | 11.9 |
| Math | 7.3 | — |
| Standard Benchmarks | ||
| GPQA | 28.3% | 73.8% |
| MMLU Pro | 41.1% | — |
| HLE | 5.2% | 10.1% |
| LiveCodeBench | 12.6% | — |
| MATH 500 | 71.7% | — |
| AIME 2025 | 7.3% | — |
| AIME (Original) | 9.7% | — |
| SciCode | 6.9% | 26.4% |
| LCR | 0.0% | 0.0% |
| IFBench | 21.1% | 34.4% |
| TAU-bench v2 | 21.6% | 46.8% |
| TerminalBench Hard | 0.0% | 1.5% |
Key Takeaways
Qwen3 1.7B (Non-reasoning) offers the best value at $0.00/1M,making it ideal for high-volume applications and cost-conscious projects.
105B (high) has the strongest reasoning profile with a 31.9 reasoning score,combining the available reasoning-heavy benchmarks.
All models support context windows of ∞+ tokens,suitable for processing lengthy documents and maintaining extended conversations.
When to Choose Each Model
Qwen3 1.7B (Non-reasoning)
- Cost-sensitive applications
- High-volume processing
105B (high)
- Complex reasoning tasks
- Research & analysis
