GPT-OSS 120B
131K context with Apache 2.0 license for full customization and self-hosting. Configurable reasoning depth with <think> tags and single 80GB GPU deployment for self-hosted RAG.
Model Information
- Provider
- OpenAI
- License
- Open Source
- Input Price per 1M
- $0.04
- Output Price per 1M
- $0.19
- Context Window
- 131K
- Release Date
- 2025-08-05
- Model Name
- gpt-oss-120b
- Total Evaluations
- 810
Performance Record
Wins153 (18.9%)
Losses553 (68.3%)
Ties104 (12.8%)
Wins
Losses
Ties
Performance Overview
ELO ratings by dataset
GPT-OSS 120B's ELO performance varies across different benchmark datasets, showing its strengths in specific domains.
GPT-OSS 120B - ELO by Dataset
Detailed Metrics
Dataset breakdown
Performance metrics across different benchmark datasets, including accuracy and latency percentiles.
MSMARCO
ELO 133815.6% WR42W-186L-42T
Quality Metrics
- Correctness
- 4.93
- Faithfulness
- 4.90
- Grounding
- 4.90
- Relevance
- 4.97
- Completeness
- 4.87
- Overall
- 4.91
Latency Distribution
- Mean
- 5616ms
- Min
- 1255ms
- Max
- 20330ms
PG
ELO 133032.2% WR87W-176L-7T
Quality Metrics
- Correctness
- 4.80
- Faithfulness
- 4.80
- Grounding
- 4.80
- Relevance
- 4.83
- Completeness
- 4.73
- Overall
- 4.79
Latency Distribution
- Mean
- 19128ms
- Min
- 1317ms
- Max
- 69491ms
SciFact
ELO 12838.9% WR24W-191L-55T
Quality Metrics
- Correctness
- 4.87
- Faithfulness
- 4.87
- Grounding
- 4.87
- Relevance
- 4.80
- Completeness
- 4.70
- Overall
- 4.82
Latency Distribution
- Mean
- 8854ms
- Min
- 0ms
- Max
- 35709ms
Compare Models
See how it stacks up
Compare GPT-OSS 120B with other top llms to understand the differences in performance, accuracy, and latency.