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

gpt-oss-20b (High)

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

Intelligence

Intelligence Index

#179 of 266
  1. 9.39.3Llama 4 Maverick
  2. 9.29.2Qwen3 Coder Next
  3. 9.29.2Motif-2-12.7B-Reasoning
  4. 9.29.2Nova Premier
  5. 9.19.1Granite 4.2 3B
  6. 99gpt-oss-20b (High)
  7. 99Mistral Small 4 (Non-reasoning)
  8. 99K2-V2 (Medium)
  9. 99Tri-21B-Think
  10. 8.98.9Gemma 4 E4B (Reasoning)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy16%#164
  • Humanity's Last Exam11%#141
  • Terminal-Bench 4.00%#96
  • AA-LCR34.7%#169
  • SciCode38.9%#110
  • CritPt1.4%#99
  • GPQA Diamond68.8%#123
  • IFBench65.1%#30
  • τ²-Bench Telecom60.2%#59
  • τ²-Bench Banking7%#75
  • Terminal-Bench Hard10.6%#57
  • APEX-Agents0.7%#10
gpt-oss-20b (High)Median
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #35 of 162
  1. 179179Claude Haiku 5.5 (Medium)
  2. 178178Mistral Small 4 (Reasoning)
  3. 177177DeepSeek V4 Flash Vision (Max)
  4. 173173Mistral Small 4 (Non-reasoning)
  5. 173173Claude Haiku 5.5 (Low)
  6. 173173gpt-oss-20b (High)
  7. 173173Nova 2.0 Lite (Low)
  8. 169169DeepSeek V4.1 Flash 1017 (Max)
  9. 168168NVIDIA Nemotron Nano 9B V2 (Non-reasoning)
  10. 166166Command A+
Data from Artificial Analysis

Latency

seconds to first token · #13 of 162
  1. 0.70.7Nemotron 3.5 Super VL
  2. 0.70.7Granite 4.2 3B
  3. 0.80.8GPT-5.6 Terra (Non-reasoning)
  4. 0.80.8gpt-oss-120b (Low)
  5. 0.80.8Qwen3 Next 80B A3B Instruct
  6. 0.80.8gpt-oss-20b (High)
  7. 0.80.8Llama 4 Scout
  8. 0.80.8Muse Spark Open (Xhigh)
  9. 0.80.8gpt-oss-120b (High)
  10. 0.80.8Granite 4.2 8B
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #18 of 169
  1. $0.070.07NVIDIA Nemotron Nano 9B V2 (Reasoning)
  2. $0.070.07Sarvam 105B (High)
  3. $0.090.09NVIDIA Nemotron Nano 9B V2 (Non-reasoning)
  4. $0.090.09NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
  5. $0.090.09NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)
  6. $0.090.09gpt-oss-20b (High)
  7. $0.10.1Nemotron 3.5 Lightning
  8. $0.10.1Ministral 3 3B
  9. $0.110.11Granite 4.2 8B
  10. $0.130.13Apertus 8B Instruct
Data from Artificial Analysis

Nearby models

  • Llama 4 MaverickMeta9.3
  • Qwen3 Coder NextAlibaba9.2
  • Motif-2-12.7B-ReasoningMotif Technologies9.2
  • Nova PremierAmazon9.2
  • Granite 4.2 3BIBM9.1
  • Mistral Small 4 (Non-reasoning)Mistral9
  • K2-V2 (Medium)Institute of Foundation Models9
  • Tri-21B-ThinkTrillion Labs9
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