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

gpt-oss-120b (Low)

  • OpenAI
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

#166 of 266
  1. 10.811G9v3-3B
  2. 10.811Qwen3.5 4B (Non-reasoning)
  3. 10.611INTELLECT-3 (Based on GLM-4.5-Air)
  4. 10.410Solar Open 100B (Reasoning)
  5. 10.310Nemotron 3 Nano Omni 30B A3B Reasoning
  6. 10.210gpt-oss-120b (Low)
  7. 1010Nova 2.0 Pro Preview (Non-reasoning)
  8. 1010gpt-oss-20b (Low)
  9. 9.910North Mini Code
  10. 9.910K2-V2 (High)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy19.8%#116
  • Humanity's Last Exam5.9%#191
  • AA-LCR46%#151
  • CritPt0%#143
  • GPQA Diamond67.2%#126
  • IFBench58.3%#43
  • τ²-Bench Telecom45%#70
  • τ²-Bench Banking2.9%#99
  • Terminal-Bench Hard5.3%#79
gpt-oss-120b (Low)Median
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #11 of 162
  1. 363363Beam 1.0
  2. 353353Trinity Large Thinking
  3. 295295Nemotron 3.5 Lightning
  4. 290290Nova Micro
  5. 277277NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)
  6. 265265gpt-oss-120b (Low)
  7. 241241NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
  8. 234234Claude Haiku 5.5 (Max)
  9. 233233gpt-oss-120b (High)
  10. 232232Qwen3.5 Omni Flash
Data from Artificial Analysis

Latency

seconds to first token · #11 of 162
  1. 0.70.7Ministral 3 3B
  2. 0.70.7Beam 1.0
  3. 0.70.7Nemotron 3.5 Super VL
  4. 0.70.7Granite 4.2 3B
  5. 0.80.8GPT-5.6 Terra (Non-reasoning)
  6. 0.80.8gpt-oss-120b (Low)
  7. 0.80.8Qwen3 Next 80B A3B Instruct
  8. 0.80.8gpt-oss-20b (High)
  9. 0.80.8Llama 4 Scout
  10. 0.80.8Muse Spark Open (Xhigh)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #54 of 169
  1. $0.220.22Phi-4
  2. $0.220.22Gemma 4 31B (Non-reasoning)
  3. $0.230.23Qwen3.8-Flash-Next
  4. $0.240.24GLM-5.3-Flash
  5. $0.240.24Hy3
  6. $0.240.24gpt-oss-120b (Low)
  7. $0.260.26MiniMax-M3.1-Flash
  8. $0.260.26gpt-oss-120b (High)
  9. $0.260.26Mistral Small 4 (Reasoning)
  10. $0.260.26Mistral Small 4 (Non-reasoning)
Data from Artificial Analysis

Nearby models

  • G9v3-3BAI9Stars10.8
  • Qwen3.5 4B (Non-reasoning)Alibaba10.8
  • INTELLECT-3 (Based on GLM-4.5-Air)Prime Intellect10.6
  • Solar Open 100B (Reasoning)Upstage10.4
  • Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIA10.3
  • Nova 2.0 Pro Preview (Non-reasoning)Amazon10
  • gpt-oss-20b (Low)OpenAI10
  • North Mini CodeCohere9.9
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