ResearchLLM Verifications Leaderboard

Data as of · 78 models, 80 questions · reviewed by Suhas Bhairav · methodology

Provider

Google AI models

6 models tested, compared with 72 models from other labs.

Best verification score83.8Gemini 4 Argon · #2 of 78Best output speed409Gemini 3.5 Flash Lite · #2 of 78Best time to first token0.6 sGemma 4 31B · #26 of 78Best cost per question$0.0011Gemma 4 26B A4B · #27 of 78
Google#2Gemini 4 Argon83.8% verification score69 tok/s3.3 s first token$0.0062 / questionGoogle#3Gemini 3.8 Flash82.5% verification score142 tok/s3.2 s first token$0.0037 / questionGoogle#9Gemini 3.1 Pro Preview77.5% verification score124 tok/s3.4 s first token$0.017 / questionGoogle#15Gemini 3.5 Flash Lite75.0% verification score409 tok/s1.1 s first token$0.0034 / questionGoogle#64Gemma 4 31B30.0% verification score58 tok/s0.6 s first token$0.0014 / questionGoogle#71Gemma 4 26B A4B15.0% verification score172 tok/s0.7 s first token$0.0011 / question

Score vs. cost per question

Google models in color, every other model in grey

Most attractive quadrant0255075100$0.00001$0.0001$0.001$0.01$0.10Cost per question (USD, log) →Verification score (%) →Qwen3.8 2.4T A95BCommand AReka Flash 3Gemma 4 26B A4BGemma 4 31BQwen3.5 397B A17BHermes 4 405BMuse WonderGrok 4.7o3gpt-oss-20bMinistral 3 3B 2512Nova Micro 1.0Phi 4Granite 4.2 8BHy3GLM 5.3 FlashSolar Pro 4Trinity Large ThinkingMiniMax M3Mistral Large 4Claude Opus 5.5GPT-6.1 SolGemini 4 ArgonGPT-5.4GPT-6 Lunagpt-oss-120bLlama 4 Maverick

Output speed vs. cost per question

Google models in color, every other model in grey

Most attractive quadrant0200400600800$0.00001$0.0001$0.001$0.01$0.10Cost per question (USD, log) →Output speed (tok/s) →Nemotron 3.5 Super VLQwen3.5 397B A17BMuse WonderGrok 4.7o3gpt-oss-20bMinistral 3 3B 2512Nova Micro 1.0Trinity Large ThinkingInkling SmallGemini 3.5 Flash LiteMuse Spark OpenGPT-6 Luna

Verification score

Google models highlighted against every model in this run · higher is better

  1. 1Claude Opus 5.585.0
  2. 2Gemini 4 Argon83.8
  3. 3GPT-5.3-Codex82.5
  4. 3Gemini 3.8 Flash82.5
  5. 5Claude Fable 5.181.2
  6. 6Grok 4.780.0
  7. 7Muse Wonder78.8
  8. 7Claude Sonnet 5.578.8
  9. 9Gemini 3.1 Pro Preview77.5
  10. 9Muse Spark Open77.5
  11. 15Gemini 3.5 Flash Lite75.0
  12. 64Gemma 4 31B30.0
  13. 71Gemma 4 26B A4B15.0

59 more models · see the full leaderboard

6 of 78 tested models have no verification score

Output speed

Google models highlighted against every model in this run · higher is better

  1. 1Nemotron 3.5 Super VL715
  2. 2Gemini 3.5 Flash Lite409
  3. 3Trinity Large Thinking329
  4. 4Ministral 3 3B 2512252
  5. 5Qwen3.5 397B A17B240
  6. 6Inkling Small233
  7. 7Muse Spark Open220
  8. 8Claude Haiku 5.5192
  9. 9Nova Micro 1.0180
  10. 10Muse Wonder175
  11. 11Gemma 4 26B A4B172
  12. 18Gemini 3.8 Flash142
  13. 26Gemini 3.1 Pro Preview124
  14. 50Gemini 4 Argon69
  15. 54Gemma 4 31B58

57 more models · see the full leaderboard

6 of 78 tested models have no output speed

Time to first token

Google models highlighted against every model in this run · lower is better

  1. 1Ministral 3 3B 25120.3 s
  2. 2Ministral 3 8B 25120.3 s
  3. 3Hermes 4 405B0.3 s
  4. 4Kimi K2.7 Code0.4 s
  5. 5MiMo-V2.6-Flash0.4 s
  6. 6Qwen3.6 35B A3B0.4 s
  7. 7Qwen3 Coder Next0.4 s
  8. 8Mistral Medium 3.50.5 s
  9. 9Phi 40.5 s
  10. 10Nova Micro 1.00.5 s
  11. 26Gemma 4 31B0.6 s
  12. 34Gemma 4 26B A4B0.7 s
  13. 47Gemini 3.5 Flash Lite1.1 s
  14. 69Gemini 3.8 Flash3.2 s
  15. 70Gemini 4 Argon3.3 s
  16. 71Gemini 3.1 Pro Preview3.4 s

58 more models · see the full leaderboard

4 of 78 tested models have no time to first token

Cost per question

Google models highlighted against every model in this run · lower is better

  1. 1Granite 4.0 Micro$0.000051
  2. 2gpt-oss-20b$0.000066
  3. 3Granite 4.2 8B$0.000077
  4. 4Nova Micro 1.0$0.000087
  5. 5Mercury 2.5$0.00011
  6. 6Phi 4$0.00012
  7. 7gpt-oss-120b$0.00013
  8. 8GLM 5.3 Flash$0.00015
  9. 9Ministral 3 3B 2512$0.00019
  10. 10GPT-6 Luna$0.00025
  11. 27Gemma 4 26B A4B$0.0011
  12. 32Gemma 4 31B$0.0014
  13. 43Gemini 3.5 Flash Lite$0.0034
  14. 45Gemini 3.8 Flash$0.0037
  15. 54Gemini 4 Argon$0.0062
  16. 69Gemini 3.1 Pro Preview$0.017

56 more models · see the full leaderboard

6 of 78 tested models have no cost per question
  • LFM2.5-2.6B: no verification score (80 of 80 questions failed on the host's side)
  • Ling 3.0 Flash VL: no verification score (not yet run on the current question suite)
  • Qwen3.5-122B-A10B: no verification score (not yet run on the current question suite)
  • Qwen3 Next 80B A3B Thinking: no verification score (not yet run on the current question suite)
  • Nova Premier 1.0: no verification score (not yet run on the current question suite)
  • GPT-5.5 Pro: no verification score (not yet run on the current question suite)

End-to-end response time

Google models highlighted against every model in this run · lower is better

  1. 1Nemotron 3.5 Super VL1.5 s
  2. 2Ministral 3 3B 25121.6 s
  3. 3Nova Micro 1.02.1 s
  4. 4Trinity Large Thinking2.7 s
  5. 5Gemini 3.5 Flash Lite2.8 s
  6. 6DeepSeek V4 Flash Vision Exp3.2 s
  7. 7Muse Spark Open3.2 s
  8. 8GLM 5.33.4 s
  9. 9Ministral 3 8B 25123.5 s
  10. 10Qwen3.5 397B A17B3.5 s
  11. 22Gemma 4 26B A4B4.8 s
  12. 32Gemini 3.8 Flash5.6 s
  13. 50Gemini 3.1 Pro Preview8.9 s
  14. 55Gemini 4 Argon9.9 s
  15. 63Gemma 4 31B12.6 s

59 more models · see the full leaderboard

4 of 78 tested models have no end-to-end response time

All Google results

Leaderboard
#
1Gemini 4 Argon
Google · served by Google
83.867 / 80693.3 s$0.0062$2 / $101M
2Gemini 3.8 Flash
Google · served by Google
82.566 / 801423.2 s$0.0037$0.825 / $4.1251M
3Gemini 3.1 Pro Preview
Google · served by Google
77.562 / 801243.4 s$0.017$2 / $121M
4Gemini 3.5 Flash Lite
Google · served by Google
75.060 / 804091.1 s$0.0034$0.3 / $2.51M
5Gemma 4 31B
Google · served by CoreWeave
30.024 / 80580.6 s$0.0014$0.2 / $0.4262k
6Gemma 4 26B A4B
Google · served by Darkbloom
15.012 / 801720.7 s$0.0011$0.09 / $0.3262k

Google: quick answers

What is the best Google model?
Gemini 4 Argon has the highest verification score of the Google models the leaderboard tested: 83.8% (67 of 80 correct) in the 2026-10-27 run.
What is the fastest Google model?
Gemini 3.5 Flash Lite is the fastest Google model the leaderboard tested, at a median 409 output tokens per second.
What is the cheapest Google model?
Gemma 4 26B A4B has the lowest billed cost per question of the Google models the leaderboard tested: $0.0011.
Which Google models do you test?
Gemini 4 Argon, Gemini 3.8 Flash, Gemini 3.1 Pro Preview, Gemini 3.5 Flash Lite, Gemma 4 31B, Gemma 4 26B A4B.