ResearchLLM Verifications Leaderboard

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

Provider

Upstage AI models

2 models tested, compared with 76 models from other labs.

Best verification score45.0Solar Pro 4 · #49 of 78Best output speed107Solar Mini 4 · #33 of 78Best time to first token0.6 sSolar Pro 4 · #23 of 78Best cost per question$0.00053Solar Mini 4 · #17 of 78
Upstage#49Solar Pro 445.0% verification score91 tok/s0.6 s first token$0.0018 / questionUpstage#54Solar Mini 441.2% verification score107 tok/s0.7 s first token$0.00053 / question

Score vs. cost per question

Upstage 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

Upstage 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

Upstage 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. 49Solar Pro 445.0
  12. 54Solar Mini 441.2

60 more models · see the full leaderboard

6 of 78 tested models have no verification score

Output speed

Upstage 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. 33Solar Mini 4107
  12. 43Solar Pro 491

60 more models · see the full leaderboard

6 of 78 tested models have no output speed

Time to first token

Upstage 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. 23Solar Pro 40.6 s
  12. 36Solar Mini 40.7 s

62 more models · see the full leaderboard

4 of 78 tested models have no time to first token

Cost per question

Upstage 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. 17Solar Mini 4$0.00053
  12. 34Solar Pro 4$0.0018

60 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

Upstage 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. 41Solar Mini 47.4 s
  12. 46Solar Pro 48.3 s

62 more models · see the full leaderboard

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

All Upstage results

Leaderboard
#
1Solar Pro 4
Upstage · served by Upstage
45.036 / 80910.6 s$0.0018$0.15 / $0.6524k
2Solar Mini 4
Upstage · served by Upstage
41.233 / 801070.7 s$0.00053$0.05 / $0.2524k

Upstage: quick answers

What is the best Upstage model?
Solar Pro 4 has the highest verification score of the Upstage models the leaderboard tested: 45.0% (36 of 80 correct) in the 2026-10-27 run.
What is the fastest Upstage model?
Solar Mini 4 is the fastest Upstage model the leaderboard tested, at a median 107 output tokens per second.
What is the cheapest Upstage model?
Solar Mini 4 has the lowest billed cost per question of the Upstage models the leaderboard tested: $0.00053.
Which Upstage models do you test?
Solar Pro 4, Solar Mini 4.