GPT-OSS 120B vs GPT-5.1
Detailed comparison between GPT-OSS 120B and GPT-5.1 for RAG applications. See which LLM best meets your accuracy, performance, and cost needs.
Model Comparison
GPT-5.1 takes the lead.
Both GPT-OSS 120B and GPT-5.1 are powerful language models designed for RAG applications. However, their performance characteristics differ in important ways.
Why GPT-5.1:
- GPT-5.1 has 441 higher ELO rating
- GPT-5.1 delivers better overall quality (4.97 vs 4.85)
- GPT-5.1 has a 50.9% higher win rate
Overview
Key metrics
ELO Rating
Overall ranking quality
GPT-OSS 120B
GPT-5.1
Win Rate
Head-to-head performance
GPT-OSS 120B
GPT-5.1
Quality Score
Overall quality metric
GPT-OSS 120B
GPT-5.1
Average Latency
Response time
GPT-OSS 120B
GPT-5.1
Visual Performance Analysis
Performance
ELO Rating Comparison
Win/Loss/Tie Breakdown
Quality Across Datasets (Overall Score)
Latency Distribution (ms)
Breakdown
How the models stack up
| Metric | GPT-OSS 120B | GPT-5.1 | Description |
|---|---|---|---|
| Overall Performance | |||
| ELO Rating | 1303 | 1743 | Overall ranking quality based on pairwise comparisons |
| Win Rate | 17.9% | 68.8% | Percentage of comparisons won against other models |
| Quality Score | 4.85 | 4.97 | Average quality across all RAG metrics |
| Pricing & Context | |||
| Input Price per 1M | $0.04 | $1.25 | Cost per million input tokens |
| Output Price per 1M | $0.19 | $10.00 | Cost per million output tokens |
| Context Window | 131K | 400K | Maximum context window size |
| Release Date | 2025-08-05 | 2025-11-13 | Model release date |
| Performance Metrics | |||
| Avg Latency | 11.2s | 16.2s | Average response time across all datasets |
Dataset Performance
By benchmark
Comprehensive comparison of RAG quality metrics (correctness, faithfulness, grounding, relevance, completeness) and latency for each benchmark dataset.
MSMARCO
| Metric | GPT-OSS 120B | GPT-5.1 | Description |
|---|---|---|---|
| Quality Metrics | |||
| Correctness | 4.93 | 4.97 | Factual accuracy of responses |
| Faithfulness | 4.90 | 4.97 | Adherence to source material |
| Grounding | 4.90 | 4.97 | Citations and context usage |
| Relevance | 4.97 | 5.00 | Query alignment and focus |
| Completeness | 4.80 | 4.93 | Coverage of all aspects |
| Overall | 4.90 | 4.97 | Average across all metrics |
| Latency Metrics | |||
| Mean | 5616ms | 9111ms | Average response time |
| Min | 1255ms | 3841ms | Fastest response time |
| Max | 20330ms | 34731ms | Slowest response time |
PG
| Metric | GPT-OSS 120B | GPT-5.1 | Description |
|---|---|---|---|
| Quality Metrics | |||
| Correctness | 4.87 | 5.00 | Factual accuracy of responses |
| Faithfulness | 4.87 | 5.00 | Adherence to source material |
| Grounding | 4.87 | 5.00 | Citations and context usage |
| Relevance | 4.90 | 5.00 | Query alignment and focus |
| Completeness | 4.83 | 4.77 | Coverage of all aspects |
| Overall | 4.87 | 4.95 | Average across all metrics |
| Latency Metrics | |||
| Mean | 19128ms | 29008ms | Average response time |
| Min | 1317ms | 4393ms | Fastest response time |
| Max | 69491ms | 43887ms | Slowest response time |
SciFact
| Metric | GPT-OSS 120B | GPT-5.1 | Description |
|---|---|---|---|
| Quality Metrics | |||
| Correctness | 4.80 | 5.00 | Factual accuracy of responses |
| Faithfulness | 4.87 | 5.00 | Adherence to source material |
| Grounding | 4.87 | 5.00 | Citations and context usage |
| Relevance | 4.77 | 4.97 | Query alignment and focus |
| Completeness | 4.67 | 4.97 | Coverage of all aspects |
| Overall | 4.79 | 4.99 | Average across all metrics |
| Latency Metrics | |||
| Mean | 8854ms | 10454ms | Average response time |
| Min | 0ms | 4700ms | Fastest response time |
| Max | 35709ms | 21205ms | Slowest response time |
Explore More
Compare more LLMs
See how all LLMs stack up for RAG applications. Compare GPT-5, Claude, Gemini, and more. View comprehensive benchmarks and find the perfect LLM for your needs.