Model Comparison
105B (high)
vs. 30B (high)
Comparing 2 AI models · 7 benchmarks · Sarvam
Recommended Pick
Sa30B (high)8 metric winsStrongest on: Value, Input price, Output price
Best Value
30B (high)
100.0 value score
25.6 reasoning / $0.05/1M
Lowest Price
30B (high)
$0.03/1M 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
Best value
30B (high) has the strongest quality-to-price mix at 100.0 out of 100 value points.
Price gap
30B (high) is 1.6x cheaper on input tokens than 105B (high).
Speed gap
30B (high) generates about 1.4x as many tokens per second as 105B (high).
Reasoning gap
105B (high) leads 30B (high) by 6.3 points on reasoning.
Top-pick rationale
30B (high) wins 8 measurable categories, including Value, Input price, Output price, Blended price.
Response Face-Off
Run one prompt through the selected models and compare response quality with live speed and cost context.
105B (high)
Sarvam
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
30B (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 | Sa 105B (high) | Top Pick Sa 30B (high) |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $0.04/1M | $0.03/1M |
| Output Cost | $0.17/1M | $0.11/1M |
| Blended (3:1) | $0.07/1M | $0.05/1M |
| Specifications | ||
| Organization | Sarvam | Sarvam |
| Release Date | Mar 6, 2026 | Mar 6, 2026 |
| Performance & Speed | ||
| Throughput | 154.6 tok/s | 221.1 tok/s |
| TTFT | 1177ms | 1134ms |
| Latency | 14117ms | 10180ms |
| Composite Indices | ||
| Value Score | 79.1 | 100.0 |
| Reasoning Score | 31.9 | 25.6 |
| Intelligence | 11.9 | 6.6 |
| Standard Benchmarks | ||
| GPQA | 73.8% | 63.3% |
| HLE | 10.1% | 7.0% |
| SciCode | 26.4% | 19.2% |
| LCR | 0.0% | 0.0% |
| IFBench | 34.4% | 26.5% |
| TAU-bench v2 | 46.8% | 34.5% |
| TerminalBench Hard | 1.5% | 2.3% |
Key Takeaways
30B (high) offers the best value at $0.03/1M,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
105B (high)
- Complex reasoning tasks
- Research & analysis
30B (high)
- Cost-sensitive applications
- High-volume processing
