Llama Nemotron Super 49B v1.5 (Reasoning) vs Gemini 3 Pro Preview (high)
Comparing 2 AI models · 6 benchmarks · NVIDIA, Google
Most Affordable
NV
Llama Nemotron Super 49B v1.5 (Reasoning)
$0.10/1M
Highest Intelligence
Go
Gemini 3 Pro Preview (high)
90.8% GPQA
Best for Coding
Go
Gemini 3 Pro Preview (high)
62.3 Coding Index
Price Difference
20.0x
input cost range
Composite Indices
Intelligence, Coding, Math
Standard Benchmarks
Academic and industry benchmarks
Benchmark Winners
6 tests
NV
Llama Nemotron Super 49B v1.5 (Reasoning)
1
- MATH 500
Go
Gemini 3 Pro Preview (high)
5
- GPQA
- MMLU Pro
- HLE
- LiveCodeBench
- AIME 2025
| Metric | NV Llama Nemotron Super 49B v1.5 (Reasoning) | Go Gemini 3 Pro Preview (high) |
|---|---|---|
| Pricing Per 1M tokens | ||
| Input Cost | $0.10/1M | $2.00/1M |
| Output Cost | $0.40/1M | $12.00/1M |
| Blended Cost 3:1 input/output ratio | $0.18/1M | $4.50/1M |
| Specifications | ||
| Organization Model creator | NVIDIA | |
| Release Date Launch date | Jul 25, 2025 | Nov 18, 2025 |
| Performance & Speed | ||
| Throughput Output speed | 75.8 tok/s | 138.9 tok/s |
| Time to First Token (TTFT) Initial response delay | 223ms | 26684ms |
| Latency Time to first answer token | 26596ms | 26684ms |
| Composite Indices | ||
| Intelligence Index Overall reasoning capability | 45.2 | 72.8 |
| Coding Index Programming ability | 37.8 | 62.3 |
| Math Index Mathematical reasoning | 76.7 | 95.7 |
| Standard Benchmarks | ||
| GPQA Graduate-level reasoning | 74.8% | 90.8% |
| MMLU Pro Advanced knowledge | 81.4% | 89.8% |
| HLE Hard language evaluation | 6.8% | 37.2% |
| LiveCodeBench Real-world coding tasks | 73.7% | 91.7% |
| MATH 500 Mathematical problems | 98.3% | |