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

MiniMax-M3.1-Flash

  • MiniMax
  • Release · October 19, 2026
  • Proprietary
  • Reasoning

Intelligence

Intelligence Index

#35 of 266
  1. 45.145DeepSeek V4.1 Flash 1017 (Max)
  2. 44.845GLM-5.3 (Max)
  3. 43.944Ling 3.1 Flash 1019
  4. 43.744Step 5 Preview
  5. 43.443Claude Haiku 5.5 (Max)
  6. 42.743MiniMax-M3.1-Flash
  7. 42.342Claude Opus 5.5 (Low)
  8. 42.242Grok 4.7 (Low)
  9. 42.142GPT-5.6 Terra (Max)
  10. 42.142GPT-6.1 Sol (Low)
Data from Artificial Analysis

Evaluations

  • AA-Briefcase1,473#16
  • AA-Omniscience Accuracy56.2%#21
  • AA-Omniscience Non-Hallucination7.2%#27
  • AutomationBench-AA72.5%#3
  • GDPval-AA1,458#18
  • Humanity's Last Exam48%#27
  • GDP.pdf20.8%#13
  • Terminal-Bench 4.025.8%#42
  • AA-LCR79.7%#51
  • SciCode53.4%#45
  • CritPt22.3%#34
  • Terminal-Bench-Science3.3%#20
  • FrontierCode38.6%#18
  • MLCR-AA16.7%#15
  • MMMU-Pro79.1%#31
  • PersonalityBench: Expressiveness18.3#24
  • PersonalityBench: Organization72.8#11
  • PersonalityBench: Transparency28.2#23
  • PersonalityBench: Slop25.8#17
  • PersonalityBench: Informativeness35.6#18
  • PersonalityBench: Warmth10.9#26
  • PersonalityBench: Conviction60.4#12
  • PersonalityBench: Imagination10.9#26
MiniMax-M3.1-FlashMedian
Data from Artificial Analysis

Cost per task

Cost per task

$ per Intelligence Index task · #5 of 24
  1. $0.070.07GPT-6 Luna (Max)
  2. $0.130.13MiMo-V2.6-Pro
  3. $0.190.19Nemotron 3.5 Super VL
  4. $0.210.21Claude Haiku 5.5 (Max)
  5. $0.220.22MiniMax-M3.1-Flash
  6. $0.230.23Beam 1.0
  7. $0.260.26DeepSeek V4.1 Flash 1017 (Max)
  8. $0.280.28GLM-5.3-Flash
  9. $0.720.72GPT-6.1 Sol (Max)
  10. $0.840.84Muse Spark Open (Xhigh)
Data from Artificial Analysis

Time per task

seconds per task · #13 of 26
  1. 364364GPT-6 Luna (Max)
  2. 396396DeepSeek V4.1 Flash 1017 (Max)
  3. 412412GPT-6 Astra (Max)
  4. 428428Claude Haiku 5.5 (Max)
  5. 498498Gemini 3.8 Flash (High)
  6. 507507MiniMax-M3.1-Flash
  7. 578578Mistral Large 4 Preview
  8. 604604GLM-5.3 (Max)
  9. 628628GPT-6.1 Sol (Max)
  10. 723723Gemini 4 Argon (High)
Data from Artificial Analysis

Tokens per task

output tokens per task · #21 of 27
  1. 68.7K69KGLM-5.3-Flash
  2. 69.5K70KMistral Large 4 Preview
  3. 71K71KGemini 3.8 Flash (High)
  4. 71.1K71KGLM-5.3 (Max)
  5. 78.1K78KClaude Fable 5.1 (Max)
  6. 78.6K79KMiniMax-M3.1-Flash
  7. 80.6K81KGrok 4.7 (Xhigh)
  8. 89.5K90KDeepSeek V4.1 Flash 1017 (Max)
  9. 107.7K108KQwen3.8 Max (0902)
  10. 119.2K119KClaude Opus 5.5 (Max)
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #78 of 162
  1. 116116GPT-5.6 Terra (Low)
  2. 115115Nova 2.0 Pro Preview (Non-reasoning)
  3. 114114GPT-5.6 Terra (Medium)
  4. 114114Gemma 4 12B (Reasoning)
  5. 114114Agnes 2.5 Pro Beta
  6. 113113MiniMax-M3.1-Flash
  7. 112112Solar Mini 4
  8. 109109Mistral Large 4 Preview
  9. 108108Claude Sonnet 5.5 (Xhigh)
  10. 108108Gemma 4 26B A4B (Non-reasoning)
Data from Artificial Analysis

Latency

seconds to first token · #54 of 162
  1. 1.21.2DeepSeek V4.1 Flash 1017 (Max)
  2. 1.31.3Quasar 438B (Max, Based on GLM-5.2)
  3. 1.31.3Trinity Large Thinking
  4. 1.31.3MiniMax-M3
  5. 1.31.3Llama 3.2 Instruct 11B (Vision)
  6. 1.41.4MiniMax-M3.1-Flash
  7. 1.41.4Claude Sonnet 5.5 (Medium)
  8. 1.41.4GPT-5.6 Terra (Low)
  9. 1.41.4Agnes 2.5 Pro Beta
  10. 1.41.4Reka Flash 3
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #55 of 169
  1. $0.220.22Gemma 4 31B (Non-reasoning)
  2. $0.230.23Qwen3.8-Flash-Next
  3. $0.240.24GLM-5.3-Flash
  4. $0.240.24Hy3
  5. $0.240.24gpt-oss-120b (Low)
  6. $0.260.26MiniMax-M3.1-Flash
  7. $0.260.26gpt-oss-120b (High)
  8. $0.260.26Mistral Small 4 (Reasoning)
  9. $0.260.26Mistral Small 4 (Non-reasoning)
  10. $0.280.28Qwen3.5 Omni Flash
Data from Artificial Analysis

Nearby models

  • DeepSeek V4.1 Flash 1017 (Max)DeepSeek45.1
  • GLM-5.3 (Max)Z AI44.8
  • Ling 3.1 Flash 1019InclusionAI43.9
  • Step 5 PreviewStepFun43.7
  • Claude Haiku 5.5 (Max)Anthropic43.4
  • Claude Opus 5.5 (Low)Anthropic42.3
  • Grok 4.7 (Low)SpaceXAI42.2
  • GPT-5.6 Terra (Max)OpenAI42.1
Data from Artificial Analysis

Same lab

  • MiniMax-M3MiniMax29.2
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend