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

Mistral Medium 3.5

  • Mistral
  • Release · April 29, 2026
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

#126 of 266
  1. 15.616Qwen3.5 122B A10B (Reasoning)
  2. 15.215Qwen3.6 35B A3B (Non-reasoning)
  3. 14.715Gemma 4 31B (Reasoning)
  4. 14.314ERNIE 5.0 Thinking Preview
  5. 14.214Nova 2.0 Pro Preview (Medium)
  6. 14.214Mistral Medium 3.5
  7. 14.214Gemma 4 12B (Reasoning)
  8. 13.914Gemma 4 31B (Non-reasoning)
  9. 13.614Nova 2.0 Omni (Medium)
  10. 13.413Nova 2.0 Lite (High)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy24.7%#92
  • Humanity's Last Exam13.8%#124
  • Terminal-Bench 4.00%#96
  • AA-LCR69.3%#111
  • SciCode40.2%#102
  • CritPt0%#143
  • AA-AnalystAgent12.5%#23
  • MMMU-Pro64.9%#74
  • GPQA Diamond74.9%#95
  • IFBench68.8%#21
  • τ²-Bench Telecom94.2%#5
  • τ²-Bench Banking15.1%#59
  • Terminal-Bench Hard33.3%#17
Mistral Medium 3.5Median
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #40 of 162
  1. 173173gpt-oss-20b (High)
  2. 173173Nova 2.0 Lite (Low)
  3. 169169DeepSeek V4.1 Flash 1017 (Max)
  4. 168168NVIDIA Nemotron Nano 9B V2 (Non-reasoning)
  5. 166166Command A+
  6. 162162Mistral Medium 3.5
  7. 162162Muse Wonder (Max)
  8. 159159Quasar 438B (Max, Based on GLM-5.2)
  9. 158158Nemotron 3 Ultra 550B A55B (Reasoning)
  10. 152152GPT-5.5 Instant (June 2026)
Data from Artificial Analysis

Latency

seconds to first token · #95 of 162
  1. 2.32.3Hermes 4 - Llama-3.1 405B (Non-reasoning)
  2. 2.32.3Qwen3.7 Plus
  3. 2.32.3Qwen3.5 122B A10B (Non-reasoning)
  4. 2.32.3Hermes 4 - Llama-3.1 405B (Reasoning)
  5. 2.32.3GPT-6 Astra (Low)
  6. 2.42.4Mistral Medium 3.5
  7. 2.42.4GLM-5.3 (Max)
  8. 2.52.5GPT-6 Luna (Low)
  9. 2.52.5Phi-4
  10. 2.62.6LongCat 2.0
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #127 of 169
  1. $33Grok 4.7 (Xhigh)
  2. $33Grok 4.7 (High)
  3. $33Qwen3.8 Max (0902)
  4. $33Grok 4.7 (Low)
  5. $33Qwen3.8 2.4T A95B
  6. $33Mistral Medium 3.5
  7. $3.443.44Nova 2.0 Pro Preview (Medium)
  8. $3.443.44Nova 2.0 Pro Preview (Low)
  9. $3.443.44Nova 2.0 Pro Preview (Non-reasoning)
  10. $3.53.5o3
Data from Artificial Analysis

Nearby models

  • Qwen3.5 122B A10B (Reasoning)Alibaba15.6
  • Qwen3.6 35B A3B (Non-reasoning)Alibaba15.2
  • Gemma 4 31B (Reasoning)Google14.7
  • ERNIE 5.0 Thinking PreviewBaidu14.3
  • Nova 2.0 Pro Preview (Medium)Amazon14.2
  • Gemma 4 12B (Reasoning)Google14.2
  • Gemma 4 31B (Non-reasoning)Google13.9
  • Nova 2.0 Omni (Medium)Amazon13.6
Data from Artificial Analysis

Same lab

  • Mistral Large 4 PreviewMistral38.4
  • Magistral Medium 1.2Mistral11.8
  • Mistral Small 4 (Reasoning)Mistral11.3
  • Mistral Small 4 (Non-reasoning)Mistral9
  • Magistral Small 1.2Mistral8.6
  • Ministral 3 14BMistral6
  • Ministral 3 8BMistral5.5
  • Ministral 3 3BMistral4.8
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend