gpt-oss-120b (high)
- Released
- Aug 5, 2025
- Tracked since
- 2026-07-23
Intelligence index11.6Ranks 339 of 664 models with this metric
Coding index30.4Ranks 164 of 259 models with this metric
Agentic index3.7Ranks 116 of 156 models with this metric
Capability profile
5 axes vs. site averagegpt-oss-120b (high)
Site average
Pricing
per 1M tokens- Input
- $0.150
- Output
- $0.590
- Cache read
- $0.130
Performance
- Output throughput
- 184 tokens/sec
- Time to first token
- 830ms
- First answer token
- 11.69s
- End-to-end response
- 14.41s
History
9Intelligence index
23.8→11.6
Output
$0.600→$0.590
Output throughput
269→184
Cheaper at this level
Models with a comparable intelligence index and a lower output price- Qwen3.5 4B (Reasoning)
AlibabaIntelligence 13.1$0.150−75%
- DeepSeek V4 Flash 0420 (Non-reasoning)
DeepSeekIntelligence 18.9$0.200−66%
- Qwen3.5 9B (Reasoning)
AlibabaIntelligence 13.7$0.200−66%
- Hy3-preview (Reasoning)
TencentIntelligence 22.7$0.210−64%
- Hy3-preview (Non-reasoning)
TencentIntelligence 17$0.210−64%