Model Comparison
GPT-4 Turbo
vs. 105B (high)
Comparing 2 AI models · 11 benchmarks · OpenAI, Sarvam
Recommended Pick
Sa 105B (high) 9 metric wins Strongest on: Value, Input price, Output price
Best Value
105B (high)
100.0 value score
34.0 reasoning / $0.07/1M
Lowest Price
105B (high)
$0.04/1M input price
Best Reasoning
105B (high)
34.0 reasoning score
Blends available reasoning benchmarks
Best for Coding
GPT-4 Turbo
21.5 coding index
Composite Indices
Higher is better; speed and price are normalized
Standard Benchmarks
Only benchmarks with data are shown
Differences That Matter
Best value
105B (high) has the strongest quality-to-price mix at 100.0 out of 100 value points.
Price gap
105B (high) is 238.1x cheaper on input tokens than GPT-4 Turbo.
Speed gap
105B (high) generates about 3.3x as many tokens per second as GPT-4 Turbo.
Reasoning gap
105B (high) leads GPT-4 Turbo by 7.6 points on reasoning.
Coding gap
GPT-4 Turbo leads 105B (high) by 11.7 points on coding.
Response Face-Off
Run one prompt through the selected models and compare response quality with live speed and cost context.
GPT-4 Turbo
OpenAI
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
105B (high)
Sarvam
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Full Comparison
| Metric | Op GPT-4 Turbo | Top Pick Sa 105B (high) |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $10.00/1M | $0.04/1M |
| Output Cost | $30.00/1M | $0.17/1M |
| Blended (3:1) | $15.00/1M | $0.07/1M |
| Specifications | ||
| Organization | OpenAI | Sarvam |
| Release Date | Nov 6, 2023 | Mar 6, 2026 |
| Performance & Speed | ||
| Throughput | 34.8 tok/s | 113.8 tok/s |
| TTFT | 1478ms | 1204ms |
| Latency | 1478ms | 18774ms |
| Composite Indices | ||
| Value Score | 0.4 | 100.0 |
| Reasoning Score | 26.4 | 34.0 |
| Intelligence | 13.7 | 18.2 |
| Coding | 21.5 | 9.8 |
| Standard Benchmarks | ||
| GPQA | — | 73.8% |
| MMLU Pro | 69.4% | — |
| HLE | 3.3% | 10.1% |
| LiveCodeBench | 29.1% | — |
| MATH 500 | 73.7% | — |
| AIME (Original) | 15.0% | — |
| SciCode | 31.9% | 26.4% |
| LCR | — | 0.0% |
| IFBench | — | 34.4% |
| TAU-bench v2 | — | 46.8% |
| TerminalBench Hard | — | 1.5% |
Key Takeaways
105B (high) offers the best value at $0.04/1M, making it ideal for high-volume applications and cost-conscious projects.
105B (high) has the strongest reasoning profile with a 34.0 reasoning score, combining the available reasoning-heavy benchmarks.
GPT-4 Turbo reaches a 21.5 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
GPT-4 Turbo
- Code generation
- Software development
105B (high)
- Cost-sensitive applications
- High-volume processing
- Complex reasoning tasks
- Research & analysis
