Llama Nemotron Super 49B v1.5 (Reasoning) vs gpt-oss-120B (high)

Comparing 2 AI models · 6 benchmarks · NVIDIA, OpenAI

Most Affordable
NVIDIA logo
Llama Nemotron Super 49B v1.5 (Reasoning)
$0.10/1M
Highest Intelligence
OpenAI logo
gpt-oss-120B (high)
78.2% GPQA
Best for Coding
OpenAI logo
gpt-oss-120B (high)
49.6 Coding Index
Price Difference
1.5x
input cost range

Composite Indices

Intelligence, Coding, Math

Standard Benchmarks

Academic and industry benchmarks

Benchmark Winners

6 tests
NVIDIA logo

Llama Nemotron Super 49B v1.5 (Reasoning)

2
  • MMLU Pro
  • MATH 500
OpenAI logo

gpt-oss-120B (high)

4
  • GPQA
  • HLE
  • LiveCodeBench
  • AIME 2025
Metric
NVIDIA logo Llama Nemotron Super 49B v1.5 (Reasoning)
NVIDIA
OpenAI logo gpt-oss-120B (high)
OpenAI
Pricing
Per 1M tokens
Input Cost $0.10/1M $0.15/1M
Output Cost $0.40/1M $0.60/1M
Blended Cost 3:1 input/output ratio
$0.18/1M $0.26/1M
Specifications
Organization Model creator
NVIDIA OpenAI
Release Date Launch date
Jul 25, 2025 Aug 5, 2025
Performance & Speed
Throughput Output speed
75.8 tok/s 332.1 tok/s
Time to First Token (TTFT) Initial response delay
223ms 576ms
Latency Time to first answer token
26596ms 6599ms
Composite Indices
Intelligence Index Overall reasoning capability
45.2 60.5
Coding Index Programming ability
37.8 49.6
Math Index Mathematical reasoning
76.7 93.4
Standard Benchmarks
GPQA Graduate-level reasoning
74.8% 78.2%
MMLU Pro Advanced knowledge
81.4% 80.8%
HLE Hard language evaluation
6.8% 18.5%
LiveCodeBench Real-world coding tasks
73.7% 87.8%
MATH 500 Mathematical problems
98.3%
AIME 2025 Advanced math competition
76.7% 93.4%
AIME (Original) Math olympiad problems
86.0%
SciCode Scientific code generation
34.8% 38.9%
LCR Code review capability
34.0% 50.7%
IFBench Instruction-following
37.0% 69.0%
TAU-bench v2 Tool use & agentic tasks
28.1% 65.8%
TerminalBench Hard CLI command generation
5.0% 22.0%

Key Takeaways

Llama Nemotron Super 49B v1.5 (Reasoning) offers the best value at $0.10/1M, making it ideal for high-volume applications and cost-conscious projects.

gpt-oss-120B (high) leads in reasoning capabilities with a 78.2% GPQA score, excelling at complex analytical tasks and problem-solving.

gpt-oss-120B (high) achieves a 49.6 coding index, making it the top choice for software development and code generation tasks.