gpt-oss-120b (low)
- Released
- Aug 5, 2025
- Tracked since
- 2026-07-23
Intelligence index10.2Ranks 369 of 664 models with this metric
Coding index21.2Ranks 196 of 259 models with this metric
Agentic index—Not tested
Capability profile
5 axes vs. site averagegpt-oss-120b (low)
Site average
Some dimensions have no data yet — marked on the chart
Pricing
per 1M tokens- Input
- $0.150
- Output
- $0.540
- Cache read
- $0.150
Performance
- Output throughput
- 181 tokens/sec
- Time to first token
- 850ms
- First answer token
- 11.91s
- End-to-end response
- 14.67s
History
5Intelligence index
14.9→10.2
Output
$0.600→$0.540
Output throughput
325→181
Cheaper at this level
Models with a comparable intelligence index and a lower output price- Qwen3.5 4B (Reasoning)
AlibabaIntelligence 13.1$0.150−72%
- Qwen3.5 4B (Non-reasoning)
AlibabaIntelligence 10.8$0.150−72%
- DeepSeek V4 Flash 0420 (Non-reasoning)
DeepSeekIntelligence 18.9$0.200−63%
- Qwen3.5 9B (Reasoning)
AlibabaIntelligence 13.7$0.200−63%
- Hy3-preview (Reasoning)
TencentIntelligence 22.7$0.210−61%