Vascend
HorizonVascend IDEVascend CLICommunityBenchmarkContact
Sign inJoin Discord
HomeHorizonIDECLISign in
ChangelogIntelligenceCost per taskCoding Agent IndexCyber IndexDecision IndexBenchmarksSpeedLatencyPriceLeaderboard
Benchmark

gpt-oss-120b (High)

  • OpenAI
  • Release · August 5, 2025
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

#149 of 266
  1. 12.212JT-MINI
  2. 11.812Nova 2.0 Lite (Low)
  3. 11.812Magistral Medium 1.2
  4. 11.712HyperNova 60B 2605 (High, Based on gpt-oss-120b)
  5. 11.712Nemotron Cascade 2 30B A3B
  6. 11.612gpt-oss-120b (High)
  7. 11.512K2 Think V2
  8. 11.512LongCat Flash Lite
  9. 11.411HyperCLOVA X SEED Think (32B)
  10. 11.311Mistral Small 4 (Reasoning)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy21.8%#108
  • Humanity's Last Exam19.6%#104
  • Terminal-Bench 4.00%#96
  • AA-LCR52%#143
  • SciCode34%#121
  • CritPt1.1%#103
  • GPQA Diamond78.2%#76
  • IFBench69%#20
  • τ²-Bench Telecom65.8%#53
  • τ²-Bench Banking12.8%#65
  • Terminal-Bench Hard23.5%#31
  • APEX-Agents3.1%#9
gpt-oss-120b (High)Median
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #14 of 162
  1. 290290Nova Micro
  2. 277277NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)
  3. 265265gpt-oss-120b (Low)
  4. 241241NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
  5. 234234Claude Haiku 5.5 (Max)
  6. 233233gpt-oss-120b (High)
  7. 232232Qwen3.5 Omni Flash
  8. 231231Nemotron 3 Nano Omni 30B A3B Reasoning
  9. 229229Step 5 Preview
  10. 223223Inkling Small
Data from Artificial Analysis

Latency

seconds to first token · #16 of 162
  1. 0.80.8gpt-oss-120b (Low)
  2. 0.80.8Qwen3 Next 80B A3B Instruct
  3. 0.80.8gpt-oss-20b (High)
  4. 0.80.8Llama 4 Scout
  5. 0.80.8Muse Spark Open (Xhigh)
  6. 0.80.8gpt-oss-120b (High)
  7. 0.80.8Granite 4.2 8B
  8. 0.80.8Gemma 4 E4B (Non-reasoning)
  9. 0.80.8NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)
  10. 0.80.8Nova Micro
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #56 of 169
  1. $0.230.23Qwen3.8-Flash-Next
  2. $0.240.24GLM-5.3-Flash
  3. $0.240.24Hy3
  4. $0.240.24gpt-oss-120b (Low)
  5. $0.260.26MiniMax-M3.1-Flash
  6. $0.260.26gpt-oss-120b (High)
  7. $0.260.26Mistral Small 4 (Reasoning)
  8. $0.260.26Mistral Small 4 (Non-reasoning)
  9. $0.280.28Qwen3.5 Omni Flash
  10. $0.280.28Granite 4.2 30B
Data from Artificial Analysis

Nearby models

  • JT-MINIChina Mobile12.2
  • Nova 2.0 Lite (Low)Amazon11.8
  • Magistral Medium 1.2Mistral11.8
  • HyperNova 60B 2605 (High, Based on gpt-oss-120b)Multiverse Computing11.7
  • Nemotron Cascade 2 30B A3BNVIDIA11.7
  • K2 Think V2Institute of Foundation Models11.5
  • LongCat Flash LiteLongCat11.5
  • HyperCLOVA X SEED Think (32B)Naver11.4
Data from Artificial Analysis

Same lab

  • GPT-6 Astra (Max)OpenAI52.7
  • GPT-6 Astra (Xhigh)OpenAI52.4
  • GPT-6.1 Sol (Max)OpenAI51.8
  • GPT-6.1 Sol (Xhigh)OpenAI51
  • GPT-6 Astra (High)OpenAI50.9
  • GPT-6.1 Sol (High)OpenAI50.2
  • GPT-6 Astra (Medium)OpenAI49.6
  • GPT-6.1 Sol (Medium)OpenAI47.8
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend