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

gpt-oss-20b (Low)

  • OpenAI
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

#168 of 266
  1. 10.611INTELLECT-3 (Based on GLM-4.5-Air)
  2. 10.410Solar Open 100B (Reasoning)
  3. 10.310Nemotron 3 Nano Omni 30B A3B Reasoning
  4. 10.210gpt-oss-120b (Low)
  5. 1010Nova 2.0 Pro Preview (Non-reasoning)
  6. 1010gpt-oss-20b (Low)
  7. 9.910North Mini Code
  8. 9.910K2-V2 (High)
  9. 9.610Qwen3 Next 80B A3B Instruct
  10. 9.510DiffusionGemma 26B A4B
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy15.1%#174
  • Humanity's Last Exam5.3%#203
  • AA-LCR31%#173
  • CritPt0%#143
  • GPQA Diamond61.1%#142
  • IFBench57.8%#46
  • τ²-Bench Telecom50.3%#64
  • Terminal-Bench Hard4.6%#81
gpt-oss-20b (Low)Median
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #25 of 162
  1. 209209Ministral 3 3B
  2. 202202NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)
  3. 195195Inkling (Xhigh)
  4. 189189Sarvam 105B (High)
  5. 186186Nova 2.0 Lite (High)
  6. 186186gpt-oss-20b (Low)
  7. 186186Claude Haiku 5.5 (Xhigh)
  8. 183183Nova 2.0 Lite (Non-reasoning)
  9. 181181Claude Haiku 5.5 (High)
  10. 180180Nova 2.0 Lite (Medium)
Data from Artificial Analysis

Latency

seconds to first token · #36 of 162
  1. 0.90.9Gemma 4 26B A4B (Reasoning)
  2. 0.90.9Qwen3.5 4B (Reasoning)
  3. 0.90.9Qwen3 Coder Next
  4. 0.90.9Mistral Small 4 (Non-reasoning)
  5. 11Gemma 4 26B A4B (Non-reasoning)
  6. 11gpt-oss-20b (Low)
  7. 11NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
  8. 11Ministral 3 14B
  9. 11Claude Sonnet 5.5 (Low)
  10. 11Llama 4 Maverick
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #23 of 169
  1. $0.090.09gpt-oss-20b (High)
  2. $0.10.1Nemotron 3.5 Lightning
  3. $0.10.1Ministral 3 3B
  4. $0.110.11Granite 4.2 8B
  5. $0.130.13Apertus 8B Instruct
  6. $0.130.13gpt-oss-20b (Low)
  7. $0.130.13Phi-4 Mini Instruct
  8. $0.140.14Phi-4 Multimodal Instruct
  9. $0.150.15Agnes 2.5 Pro Beta
  10. $0.150.15Gemma 4 12B (Reasoning)
Data from Artificial Analysis

Nearby models

  • 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
  • gpt-oss-120b (Low)OpenAI10.2
  • Nova 2.0 Pro Preview (Non-reasoning)Amazon10
  • North Mini CodeCohere9.9
  • K2-V2 (High)Institute of Foundation Models9.9
  • Qwen3 Next 80B A3B InstructAlibaba9.6
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