Llama Nemotron Super 49B v1.5 (Reasoning)
Analysis Summary
This is NVIDIA's reasoning-mode configuration of the Nemotron Super 49B v1.5, priced at $0.10 per million input tokens and $0.40 output. In reasoning mode, it achieves a strong AIME 25 score of 0.767 and livecodebench of 0.737, indicating genuine mathematical and code-generation capability when given extended compute for chain-of-thought.
However, the overall intelligence index of 18.7 and coding index of 15.1 reflect that these gains are task-specific rather than broadly generalised. Agentic performance at 16.7 is low, and long-context reliability at 0.34 limits its usefulness for document-heavy workflows. The terminalbench score is also weak.
At its price point, this model suits teams with specific mathematical or competitive-coding workloads who can leverage reasoning mode effectively. For general business automation, content, or agent tasks, stronger alternatives are available at comparable cost.
Assessed June 6, 2026
Editorial notes
Llama Nemotron Super 49B v1.5 (Reasoning) shows strong math and livecodebench scores in reasoning mode, with AIME 25 at 0.767, but agentic and general intelligence indices remain modest for a 49B-class model at $0.10 input.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Llama Nemotron Super 49B v1.5 (Reasoning) compares
Llama Nemotron Super 49B v1.5 (Reasoning) ranks #185 of 378 AI models we track for overall intelligence, #179 of 315 for coding, #201 of 289 for agentic tasks. At $0.10 per million input tokens it is cheaper than 66% of comparable models.
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Llama Nemotron Super 49B v1.5 (Reasoning) stack up?
Compare side-by-side with other professional models.
Model Information
| Provider | NVIDIA |
| Release Date | July 25, 2025 |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.10 | $0.000100 |
| Output | $0.40 | $0.000400 |
Leaderboard Categories
Frequently asked questions about Llama Nemotron Super 49B v1.5 (Reasoning)
How much does Llama Nemotron Super 49B v1.5 (Reasoning) cost?
Llama Nemotron Super 49B v1.5 (Reasoning) costs $0.10 per million input tokens and $0.40 per million output tokens.
Is Llama Nemotron Super 49B v1.5 (Reasoning) good for coding?
On our coding benchmark index, Llama Nemotron Super 49B v1.5 (Reasoning) ranks #179 of 315 models, placing it in the broader range of the field for code generation and debugging.
Who created Llama Nemotron Super 49B v1.5 (Reasoning)?
Llama Nemotron Super 49B v1.5 (Reasoning) is developed by NVIDIA and was released on July 25, 2025.
