Benchmarks / UGI Leaderboard

Reported by UGI Leaderboard

UGI Leaderboard

How closely the model matches the writing style of a given example.

Last updated 2 Oct 2026

Results dated
6 Sep 2025 to 2 Oct 2026
Results
379 configurations of 230 models
Unit
score from 0 to 1
Licence
Apache License 2.0

Style adherence: Gemini 3.1 Pro Preview

Top 15 of 379 results · score from 0 to 1, higher is better · ≈ cannot be told apart from the leader. Choose a model to highlight it.Clear highlight

  1. 1≈ Claude Opus 5.5 (max reasoning)Anthropic 0.43
  2. 1≈ Claude Opus 5.5 (medium reasoning)Anthropic 0.43
  3. 1≈ Claude Fable 5.1 (high reasoning)Anthropic 0.43
  4. 1≈ Claude Opus 5.5 (high reasoning)Anthropic 0.43
  5. 5 Claude Opus 5.5 (extra-high reasoning)Anthropic 0.42
  6. 5 Claude Fable 5.1 (medium reasoning)Anthropic 0.42
  7. 5 Claude Opus 4.6 (high reasoning)Anthropic 0.42
  8. 8 Claude Opus 4.7 (high reasoning)Anthropic 0.41
  9. 8 Claude Sonnet 4.6 (max reasoning)Anthropic 0.41
  10. 8 Claude Sonnet 4.6 (medium reasoning)Anthropic 0.41
  11. 8 GPT-5.5 (high reasoning)OpenAI 0.41
  12. 8 Claude Opus 4.6 (medium reasoning)Anthropic 0.41
  13. 8 MiniMax-M2.1MiniMax 0.41
  14. 8 Claude Opus 4.6 (max reasoning)Anthropic 0.41
  15. 8 GPT-5.5 (medium reasoning)OpenAI 0.41
  16. 218 Gemini 3.1 Pro Preview (low reasoning)Google 0.34
  17. 249 Gemini 3.1 Pro Preview (high reasoning)Google 0.33
  18. 249 Gemini 3.1 Pro Preview (medium reasoning)Google 0.33

Full results

UGI: style adherence, score from 0 to 1, higher is better
#ModelStyle adherence
score from 0 to 1, higher is better		Price
$ per million tokens, in / out
1≈ Claude Opus 5.5 (max reasoning)Anthropic
0.43
$4 / $20
1≈ Claude Opus 5.5 (medium reasoning)Anthropic
0.43
$4 / $20
1≈ Claude Fable 5.1 (high reasoning)Anthropic
0.43
$10 / $50
1≈ Claude Opus 5.5 (high reasoning)Anthropic
0.43
$4 / $20
5 Claude Opus 5.5 (extra-high reasoning)Anthropic
0.42
$4 / $20
5 Claude Fable 5.1 (medium reasoning)Anthropic
0.42
$10 / $50
5 Claude Opus 4.6 (high reasoning)Anthropic
0.42
$5 / $25
8 Claude Opus 4.7 (high reasoning)Anthropic
0.41
$5 / $25
8 Claude Sonnet 4.6 (max reasoning)Anthropic
0.41
$3 / $15
8 Claude Sonnet 4.6 (medium reasoning)Anthropic
0.41
$3 / $15
8 GPT-5.5 (high reasoning)OpenAI
0.41
$5 / $30
8 Claude Opus 4.6 (medium reasoning)Anthropic
0.41
$5 / $25
8 MiniMax-M2.1MiniMax
0.41
$0.30 / $1.20
8 Claude Opus 4.6 (max reasoning)Anthropic
0.41
$5 / $25
8 GPT-5.5 (medium reasoning)OpenAI
0.41
$5 / $30
8 Claude Sonnet 4.5 (reasoning on)Anthropic
0.41
$3 / $15
8 Claude Fable 5 (extra-high reasoning)Anthropic
0.41
$10 / $50
8 GPT-5.5 (low reasoning)OpenAI
0.41
$5 / $30
19 Claude Opus 4.7 (medium reasoning)Anthropic
0.40
$5 / $25
19 Claude Opus 4.8 (max reasoning)Anthropic
0.40
$5 / $25
19 GPT-5.5 (extra-high reasoning)OpenAI
0.40
$5 / $30
19 Claude Opus 5.5 (low reasoning)Anthropic
0.40
$4 / $20
19 Claude Opus 4.7 (max reasoning)Anthropic
0.40
$5 / $25
19 MiMo-V2.5-Pro (reasoning on)Xiaomi
0.40
$0.43 / $0.87
19 MiMo-V2.5 (reasoning on)Xiaomi
0.40
$0.17 / $0.34
19 GLM-5 (no reasoning)Z.ai
0.40
$0.95 / $2.55
19 Trinity Large PreviewArcee AI
0.40
–
19 GPT-5.4 (high reasoning)OpenAI
0.40
$2.50 / $15
19 Gemini 2.5 ProGoogle
0.40
$1.25 / $10
19 Claude Fable 5 (high reasoning)Anthropic
0.40
$10 / $50
19 Claude Opus 4.6 (low reasoning)Anthropic
0.40
$5 / $25
19 GPT-5.4 (extra-high reasoning)OpenAI
0.40
$2.50 / $15
19 GPT-5.5 (no reasoning)OpenAI
0.40
$5 / $30
19 GPT-5.2 (low reasoning)OpenAI
0.40
$1.75 / $14
35 Claude Fable 5.1 (low reasoning)Anthropic
0.39
$10 / $50
35 Claude Sonnet 4.6 (high reasoning)Anthropic
0.39
$3 / $15
35 GPT-5.4 (medium reasoning)OpenAI
0.39
$2.50 / $15
35 GPT-5.6 Terra (extra-high reasoning)OpenAI
0.39
$2 / $12
35 Claude Sonnet 4.6 (low reasoning)Anthropic
0.39
$3 / $15
35 GPT-6 Sol (extra-high reasoning)OpenAI
0.39
$2 / $10
35 Claude Fable 5 (low reasoning)Anthropic
0.39
$10 / $50
35 Claude Opus 4.5 (reasoning on)Anthropic
0.39
$5 / $25
35 GPT-5 (high reasoning)OpenAI
0.39
$1.25 / $10
35 Claude Haiku 4.5 (reasoning on)Anthropic
0.39
$1 / $5
35 Claude Opus 4.7 (low reasoning)Anthropic
0.39
$5 / $25
35 GPT-5.6 Terra (medium reasoning)OpenAI
0.39
$2 / $12
35 GLM-4.6V (no reasoning)Z.ai
0.39
$0.30 / $0.90
35 GLM-4.6V (reasoning on)Z.ai
0.39
$0.30 / $0.90
35 Claude Opus 4.8 (extra-high reasoning)Anthropic
0.39
$5 / $25
35 Mistral Medium 3.1Mistral AI
0.39
$0.40 / $2
35 GPT-5.6 Terra (low reasoning)OpenAI
0.39
$2 / $12
52 Kimi K2 ThinkingMoonshot AI
0.38
$0.60 / $2.50
52 GPT-6 Sol (high reasoning)OpenAI
0.38
$2 / $10
52 Claude Opus 4.8 (low reasoning)Anthropic
0.38
$5 / $25
52 MiniMax-M2.7MiniMax
0.38
$0.30 / $1.20
52 Claude Fable 5 (medium reasoning)Anthropic
0.38
$10 / $50
52 GPT-5.1 (low reasoning)OpenAI
0.38
$1.25 / $10
52 GLM-5.1 (reasoning on)Z.ai
0.38
$1.38 / $4.40
52 GPT-5.6 Terra (high reasoning)OpenAI
0.38
$2 / $12
52 GPT-6 Sol (low reasoning)OpenAI
0.38
$2 / $10
52 Qwen3-1.7B (no reasoning)Alibaba
0.38
–
52 GPT-5.4 (no reasoning)OpenAI
0.38
$2.50 / $15
52 GPT-5.6 Luna (extra-high reasoning)OpenAI
0.38
$0.20 / $1.20
52 GLM-5 (reasoning on)Z.ai
0.38
$0.95 / $2.55
52 Claude Opus 4.8 (high reasoning)Anthropic
0.38
$5 / $25
52 GPT-5.2 (high reasoning)OpenAI
0.38
$1.75 / $14
52 GPT-5.4 (low reasoning)OpenAI
0.38
$2.50 / $15
52 GPT-5.2 (no reasoning)OpenAI
0.38
$1.75 / $14
52 GPT-5.6 Luna (medium reasoning)OpenAI
0.38
$0.20 / $1.20
52 GPT-6 Sol (medium reasoning)OpenAI
0.38
$2 / $10
52 Claude Sonnet 5 (extra-high reasoning)Anthropic
0.38
$2 / $10
52 Llama 3.1 70B InstructMeta
0.38
$0.40 / $0.40
52 GLM-4.6 (reasoning on)Z.ai
0.38
$0.50 / $2
52 GLM-4.7 (reasoning on)Z.ai
0.38
$0.54 / $1.98
52 Claude Fable 5 (max reasoning)Anthropic
0.38
$10 / $50
52 Claude Sonnet 4.5 (no reasoning)Anthropic
0.38
$3 / $15
52 MiniMax-M2.5MiniMax
0.38
$0.30 / $1.20
52 Mistral Large 3 (no reasoning)Mistral AI
0.38
$0.50 / $1.50
52 GPT-5.6 Terra (no reasoning)OpenAI
0.38
$2 / $12
52 GPT-6 Astra (medium reasoning)OpenAI
0.38
$10 / $50
52 GPT-6 Astra (extra-high reasoning)OpenAI
0.38
$10 / $50
52 Claude Opus 4.1 (reasoning on)Anthropic
0.38
$15 / $75
52 Claude Sonnet 5 (medium reasoning)Anthropic
0.38
$2 / $10
84 GLM-5.1 (no reasoning)Z.ai
0.37
$1.38 / $4.40
84 GPT-6.1 Sol (high reasoning)OpenAI
0.37
$2 / $10
84 Step 3.5 FlashStepFun
0.37
$0.10 / $0.30
84 GLM-4.6 (no reasoning)Z.ai
0.37
$0.50 / $2
84 GLM-5.2 (no reasoning)Z.ai
0.37
$1.40 / $4.40
84 DeepSeek-V3DeepSeek
0.37
$0.26 / $1.03
84 Mistral Large 3 (reasoning on)Mistral AI
0.37
$0.50 / $1.50
84 GPT-5.1 (medium reasoning)OpenAI
0.37
$1.25 / $10
84 GPT-5.6 Luna (high reasoning)OpenAI
0.37
$0.20 / $1.20
84 DeepSeek-V3.1-Terminus (reasoning on)DeepSeek
0.37
$0.27 / $1
84 GPT-5.6 Sol (extra-high reasoning)OpenAI
0.37
$4 / $20
84 Qwen3-4B (no reasoning)Alibaba
0.37
–
84 Claude Sonnet 5 (high reasoning)Anthropic
0.37
$2 / $10
84 Llama 4 MaverickMeta
0.37
$0.27 / $0.85
84 Muse Glimmer 30B (medium reasoning)Meta
0.37
$0.30 / $1.20
84 GPT-5.2 (medium reasoning)OpenAI
0.37
$1.75 / $14
84 GPT-5.6 Luna (low reasoning)OpenAI
0.37
$0.20 / $1.20
84 GPT-6.1 Sol (extra-high reasoning)OpenAI
0.37
$2 / $10
84 GLM-4.7-Flash (reasoning by prefill)Z.ai
0.37
$0.06 / $0.40
84 Qwen3-1.7B (reasoning on)Alibaba
0.37
–
84 Qwen3-14B (no reasoning)Alibaba
0.37
$0.12 / $0.24
84 Claude Opus 4.8 (medium reasoning)Anthropic
0.37
$5 / $25
84 Gemini 3 Pro Preview (high reasoning)Google
0.37
–
84 GPT-5 (low reasoning)OpenAI
0.37
$1.25 / $10
84 GPT-6.1 Sol (low reasoning)OpenAI
0.37
$2 / $10
84 GPT-6.1 Sol (medium reasoning)OpenAI
0.37
$2 / $10
84 Llama 3.3 70B InstructMeta
0.37
$0.59 / $0.79
84 GPT-5.1 (high reasoning)OpenAI
0.37
$1.25 / $10
84 Claude Sonnet 5 (max reasoning)Anthropic
0.37
$2 / $10
84 Gemini 3 Flash Preview (high reasoning)Google
0.37
$0.50 / $3
84 GPT-6 Astra (low reasoning)OpenAI
0.37
$10 / $50
84 GLM-4.7 (no reasoning)Z.ai
0.37
$0.54 / $1.98
84 Claude Opus 4.5 (no reasoning)Anthropic
0.37
$5 / $25
84 DeepSeek-V3.2-SpecialeDeepSeek
0.37
–
84 Muse Glimmer 30B (high reasoning)Meta
0.37
$0.30 / $1.20
84 Grok 4.7xAI
0.37
$2 / $6
84 Jamba Mini 1.7AI21 Labs
0.37
–
84 DeepSeek-V3.2 (reasoning on)DeepSeek
0.37
$0.30 / $0.96
84 DeepSeek-V4-Flash (0423, reasoning on)DeepSeek
0.37
$0.14 / $0.28
84 Gemini 3 Flash Preview (medium reasoning)Google
0.37
$0.50 / $3
84 MiniMax-M2MiniMax
0.37
$0.30 / $1.20
84 Mistral Large 2.1 (2411)Mistral AI
0.37
–
126 Qwen3-4B (reasoning on)Alibaba
0.36
–
126 Qwen3-8B (no reasoning)Alibaba
0.36
$0.12 / $0.46
126 Claude Opus 4 (reasoning on)Anthropic
0.36
–
126 Llama 3.1 405B InstructMeta
0.36
–
126 Mistral Large 2 (2407)Mistral AI
0.36
$2 / $6
126 GPT-5.6 Sol (low reasoning)OpenAI
0.36
$4 / $20
126 MiMo-V2.5-Pro (no reasoning)Xiaomi
0.36
$0.43 / $0.87
126 Qwen2.5-72B-InstructAlibaba
0.36
$0.36 / $0.40
126 Qwen3-235B-A22B-Instruct-2507Alibaba
0.36
$0.15 / $0.75
126 GPT-6 Astra (high reasoning)OpenAI
0.36
$10 / $50
126 Qwen3-30B-A3B (no reasoning)Alibaba
0.36
$0.12 / $0.50
126 DeepSeek-V3.1 (reasoning on)DeepSeek
0.36
$0.55 / $1.65
126 DeepSeek-V3.1-Terminus (no reasoning)DeepSeek
0.36
$0.27 / $1
126 Llama 4 ScoutMeta
0.36
$0.18 / $0.59
126 GPT-5.3 ChatOpenAI
0.36
–
126 o1 (high reasoning)OpenAI
0.36
$15 / $60
126 Grok 3xAI
0.36
–
126 MiMo-V2.5 (no reasoning)Xiaomi
0.36
$0.17 / $0.34
126 MiMo-V2-Flash (no reasoning)Xiaomi
0.36
–
126 Gemma 4 31B (reasoning by prefill)Google
0.36
$0.14 / $0.40
126 GPT-5.6 Luna (no reasoning)OpenAI
0.36
$0.20 / $1.20
126 Falcon-H1 0.5B InstructTII
0.36
–
126 GLM-4.5 (reasoning on)Z.ai
0.36
$0.60 / $2.20
126 Jamba Large 1.7AI21 Labs
0.36
–
126 Claude Sonnet 4 (no reasoning)Anthropic
0.36
$3 / $15
126 DeepSeek-V4-Pro (0423, reasoning on)DeepSeek
0.36
$1.42 / $2.83
126 Rnj-1 InstructEssential AI
0.36
–
126 Mixtral 8x7B Instruct v0.1Mistral AI
0.36
–
126 Grok 4.6xAI
0.36
$2 / $6
126 Gemini 3 Pro Preview (low reasoning)Google
0.36
–
126 Llama 3.2 3B InstructMeta
0.36
$0.05 / $0.33
126 Qwen3-30B-A3B (reasoning on)Alibaba
0.36
$0.12 / $0.50
126 Qwen3.5-122B-A10B (no reasoning)Alibaba
0.36
$0.26 / $2.08
126 Claude Sonnet 4 (reasoning on)Anthropic
0.36
$3 / $15
126 Grok 4 (0709)xAI
0.36
–
126 Grok 4.20 Multi-Agent Beta (0309, 4 agents)xAI
0.36
–
126 Qwen3-VL-235B-A22B-InstructAlibaba
0.36
$0.30 / $1.50
126 Seed-OSS-36B-InstructByteDance
0.36
–
126 GPT-5.6 Sol (high reasoning)OpenAI
0.36
$4 / $20
126 GPT-5.6 Sol (no reasoning)OpenAI
0.36
$4 / $20
166 Qwen3.5-122B-A10B (reasoning on)Alibaba
0.35
$0.26 / $2.08
166 Qwen3-14B (reasoning on)Alibaba
0.35
$0.12 / $0.24
166 Claude 3.7 Sonnet (reasoning on)Anthropic
0.35
–
166 Claude Sonnet 5 (low reasoning)Anthropic
0.35
$2 / $10
166 Llama 2 70B ChatMeta
0.35
–
166 Muse Glimmer 30B (extra-high reasoning)Meta
0.35
$0.30 / $1.20
166 Mistral Small 3.1 24BMistral AI
0.35
$0.35 / $0.56
166 ChatGPT-4o (2025-03-26)OpenAI
0.35
–
166 Grok 4.20 Beta (0309, non-reasoning)xAI
0.35
–
166 Claude Opus 4 (no reasoning)Anthropic
0.35
–
166 Command R (08-2024)Cohere
0.35
$0.15 / $0.60
166 Gemma 4 26B A4B (reasoning by prefill)Google
0.35
$0.10 / $0.30
166 Mistral Medium 3Mistral AI
0.35
$0.40 / $2
166 GPT-5.6 Sol (medium reasoning)OpenAI
0.35
$4 / $20
166 GLM-4.5 (no reasoning)Z.ai
0.35
$0.60 / $2.20
166 GLM-4.7-Flash (no reasoning)Z.ai
0.35
$0.06 / $0.40
166 Qwen3.6-Plus (no reasoning)Alibaba
0.35
$0.33 / $1.95
166 DeepSeek-V4-Pro (0423, no reasoning)DeepSeek
0.35
$1.42 / $2.83
166 Gemini 3.5 Flash (medium reasoning)Google
0.35
$1.50 / $9
166 Granite 4.0 H SmallIBM
0.35
–
166 GPT-5 Chat (latest)OpenAI
0.35
–
166 Qwen3-VL-32B-InstructAlibaba
0.35
$0.10 / $0.42
166 Llama 3.3 8B InstructAllura Forge
0.35
–
166 Claude Haiku 4.5 (no reasoning)Anthropic
0.35
$1 / $5
166 Mixtral 8x22B InstructMistral AI
0.35
$2 / $6
166 Muse Glimmer 30B (low reasoning)Meta
0.35
$0.30 / $1.20
166 Mistral Small 3Mistral AI
0.35
$0.05 / $0.08
166 Qwen3-8B (reasoning on)Alibaba
0.35
$0.12 / $0.46
166 DeepSeek-V3-0324DeepSeek
0.35
$0.25 / $1
166 Mistral Small 3.2 24BMistral AI
0.35
$0.094 / $0.25
166 Mistral Small (2409)Mistral AI
0.35
–
166 GPT-5.2 ChatOpenAI
0.35
–
166 o1 (low reasoning)OpenAI
0.35
$15 / $60
166 Qwen3.6-27B (no reasoning)Alibaba
0.35
$0.30 / $3.20
166 Nova 2 Lite (no reasoning)Amazon
0.35
$0.30 / $2.50
166 Ministral 3 14B ReasoningMistral AI
0.35
–
166 Mistral Medium 3.5 (no reasoning)Mistral AI
0.35
$1.50 / $7.50
166 Kimi K2.6 (reasoning on)Moonshot AI
0.35
$0.95 / $4
166 GLM-5.2 (reasoning on)Z.ai
0.35
$1.40 / $4.40
166 Claude 3 OpusAnthropic
0.35
–
166 Command ACohere
0.35
$2.50 / $10
166 DeepSeek-V3.2-Exp (no reasoning)DeepSeek
0.35
$0.27 / $0.41
166 DeepSeek-V3.2-Exp (reasoning on)DeepSeek
0.35
$0.27 / $0.41
166 Devstral Small 2Mistral AI
0.35
–
166 Qwen3-4B-Instruct-2507Alibaba
0.35
–
166 Claude Opus 4.1 (no reasoning)Anthropic
0.35
$15 / $75
166 Seed-OSS-36B-Instruct (512-token reasoning budget)ByteDance
0.35
–
166 Gemini 2.5 Flash Preview (09-2025, reasoning on)Google
0.35
–
166 Gemini 3.5 Flash (low reasoning)Google
0.35
$1.50 / $9
166 Gemma 4 12BGoogle
0.35
–
166 Ministral 3 8B Reasoning (reasoning by prefill)Mistral AI
0.35
–
166 Hy3 Preview (no reasoning)Tencent
0.35
$0.18 / $0.60
218 Qwen3-VL-235B-A22B-ThinkingAlibaba
0.34
$0.40 / $4
218 Gemini 3.1 Pro Preview (low reasoning)Google
0.34
$2 / $12
218 Gemma 4 31BGoogle
0.34
$0.14 / $0.40
218 Llama 3.1 8B InstructMeta
0.34
$0.05 / $0.08
218 Phi-4Microsoft
0.34
$0.07 / $0.14
218 Ministral 3 8B ReasoningMistral AI
0.34
–
218 Seed-OSS-36B-Instruct (no reasoning)ByteDance
0.34
–
218 Gemma 4 26B A4BGoogle
0.34
$0.10 / $0.30
218 Inflection 3 PiInflection AI
0.34
–
218 Magistral Small 1.2Mistral AI
0.34
–
218 Kimi K2.5 (no reasoning)Moonshot AI
0.34
$0.57 / $2.85
218 Kimi K2.6 (no reasoning)Moonshot AI
0.34
$0.95 / $4
218 Grok 4.20 (0309, non-reasoning)xAI
0.34
–
218 Command R+ (08-2024)Cohere
0.34
$2.50 / $10
218 DeepSeek-V3.1 (no reasoning)DeepSeek
0.34
$0.55 / $1.65
218 Nova 2 Lite (reasoning on)Amazon
0.34
$0.30 / $2.50
218 Claude 3 HaikuAnthropic
0.34
–
218 Gemini 2.5 Flash Preview (09-2025, no reasoning)Google
0.34
–
218 Gemini 3.5 Flash (high reasoning)Google
0.34
$1.50 / $9
218 Gemini 3 Flash Preview (minimal reasoning)Google
0.34
$0.50 / $3
218 Gemini 3.8 Flash (high reasoning)Google
0.34
$1.50 / $7.50
218 Kimi K2.5 (reasoning on)Moonshot AI
0.34
$0.57 / $2.85
218 Kimi-VL-A3B-InstructMoonshot AI
0.34
–
218 DeepSeek-V3.2 (no reasoning)DeepSeek
0.34
$0.30 / $0.96
218 EXAONE 4.0 32BLG AI Research
0.34
–
218 Mistral NemoMistral AI
0.34
$0.023 / $0.03
218 GPT-5.1 ChatOpenAI
0.34
–
218 Grok 4.3xAI
0.34
$1.25 / $2.50
218 MiMo-V2-Flash (reasoning on)Xiaomi
0.34
–
218 Qwen3-VL-32B-ThinkingAlibaba
0.34
–
218 Gemini 3.8 Flash (medium reasoning)Google
0.34
$1.50 / $7.50
249 Kimi-VL-A3B-Thinking (2506)Moonshot AI
0.33
–
249 Qwen3-30B-A3B-Thinking-2507Alibaba
0.33
$0.20 / $2.40
249 Qwen3-VL-4B-ThinkingAlibaba
0.33
–
249 Qwen3-VL-8B-InstructAlibaba
0.33
$0.12 / $0.46
249 Gemma 4 12B (reasoning by prefill)Google
0.33
–
249 MedGemma 27B TextGoogle
0.33
–
249 Llama 3.2 1B InstructMeta
0.33
$0.027 / $0.20
249 Ministral 3 8B (reasoning by prefill)Mistral AI
0.33
$0.15 / $0.15
249 o4-mini (low reasoning)OpenAI
0.33
$1.10 / $4.40
249 Qwen3.5-27B (no reasoning)Alibaba
0.33
$0.27 / $2.16
249 Qwen3-VL-2B-ThinkingAlibaba
0.33
–
249 Gemini 3.1 Pro Preview (high reasoning)Google
0.33
$2 / $12
249 Grok 4.1 Fast (reasoning)xAI
0.33
–
249 Grok 4.20 Beta (0309, reasoning)xAI
0.33
–
249 Qwen3.5-2B (reasoning by prefill)Alibaba
0.33
–
249 Qwen3.5-35B-A3B (no reasoning)Alibaba
0.33
$0.16 / $1.30
249 GPT-4o (2024-05-13)OpenAI
0.33
$5 / $15
249 Ling-1TAnt Group
0.33
–
249 Ministral 3 8BMistral AI
0.33
$0.15 / $0.15
249 Qwen3-MaxAlibaba
0.33
$0.78 / $3.90
249 Qwen3-VL-8B-ThinkingAlibaba
0.33
$0.18 / $2.10
249 Gemini 3.1 Pro Preview (medium reasoning)Google
0.33
$2 / $12
249 Gemini 3.5 Flash (minimal reasoning)Google
0.33
$1.50 / $9
249 Hy3 Preview (reasoning on)Tencent
0.33
$0.18 / $0.60
249 Grok 4 Fast (reasoning)xAI
0.33
–
249 GLM-4.5-AirZ.ai
0.33
$0.14 / $0.86
249 DeepSeek-V4-Flash (0423, no reasoning)DeepSeek
0.33
$0.14 / $0.28
249 Gemini 3.6 Flash (medium reasoning)Google
0.33
$1.50 / $7.50
249 Gemini 3.7 Flash (medium reasoning)Google
0.33
$1.50 / $7.50
249 GPT-4.1OpenAI
0.33
$2 / $8
249 Falcon-H1 3B InstructTII
0.33
–
249 Grok 4 Fast (non-reasoning)xAI
0.33
–
249 Qwen3.5-397B-A17B (no reasoning)Alibaba
0.33
$0.55 / $3.50
249 Qwen3.6-Plus (reasoning on)Alibaba
0.33
$0.33 / $1.95
249 Claude 3.7 Sonnet (no reasoning)Anthropic
0.33
–
249 Falcon-H1 7B InstructTII
0.33
–
249 Grok 4.20 (0309, reasoning)xAI
0.33
–
286 Ministral 3 14BMistral AI
0.32
$0.20 / $0.20
286 Gemma 4 E2B (reasoning by prefill)Google
0.32
–
286 Gemini 3.7 Flash (high reasoning)Google
0.32
$1.50 / $7.50
286 Qwen2.5-VL-72B-InstructAlibaba
0.32
$0.80 / $1
286 Falcon-H1 1.5B InstructTII
0.32
–
286 Solar Pro 3Upstage
0.32
$0.15 / $0.60
286 GLM-4-32B-0414Z.ai
0.32
–
286 Qwen3.5-9B (no reasoning)Alibaba
0.32
$0.10 / $0.15
286 Qwen3.6-35B-A3B (no reasoning)Alibaba
0.32
$0.10 / $1
286 Gemini 3.6 Flash (high reasoning)Google
0.32
$1.50 / $7.50
286 Gemini 3.8 Flash (low reasoning)Google
0.32
$1.50 / $7.50
286 Ministral 3 14B Reasoning (reasoning by prefill)Mistral AI
0.32
–
286 Qwen3-32B (no reasoning)Alibaba
0.32
$0.14 / $0.40
286 Qwen3.5-4B (no reasoning)Alibaba
0.32
–
286 Kimi Linear 48B A3B InstructMoonshot AI
0.32
–
286 Qwen2.5-7B-InstructAlibaba
0.32
$0.10 / $0.20
286 Qwen2.5-VL-32B-InstructAlibaba
0.32
–
286 Ring-1TAnt Group
0.32
–
286 Grok 4.1 Fast (non-reasoning)xAI
0.32
–
286 Grok 4.5xAI
0.32
$2 / $6
286 Qwen2.5-Coder-7B-InstructAlibaba
0.32
–
286 Qwen3.5-0.8B (no reasoning)Alibaba
0.32
–
286 Olmo 3 32B ThinkAi2
0.32
–
286 DeepSeek-R1-0528DeepSeek
0.32
$0.50 / $2.18
286 Ministral 3 8B Reasoning (reasoning by system prompt)Mistral AI
0.32
–
311 Qwen3-30B-A3B-Instruct-2507Alibaba
0.31
$0.09 / $0.30
311 gpt-oss-20b (medium reasoning)OpenAI
0.31
$0.03 / $0.15
311 o4-mini (medium reasoning)OpenAI
0.31
$1.10 / $4.40
311 Qwen3-VL-30B-A3B-ThinkingAlibaba
0.31
$0.29 / $1
311 Ministral 3 14B (reasoning by prefill)Mistral AI
0.31
$0.20 / $0.20
311 Falcon-H1 1.5B Deep InstructTII
0.31
–
311 o4-mini (high reasoning)OpenAI
0.31
$1.10 / $4.40
311 Apriel Nemotron 15B ThinkerServiceNow
0.31
–
311 Qwen3.5-27B (reasoning by prefill)Alibaba
0.31
$0.27 / $2.16
311 Gemma 4 E2BGoogle
0.31
–
311 Mistral Small 4 (high reasoning)Mistral AI
0.31
$0.15 / $0.60
311 Mistral Medium 3.5 (high reasoning)Mistral AI
0.31
$1.50 / $7.50
311 Reka Flash 3Reka AI
0.31
$0.10 / $0.20
311 Qwen3-235B-A22B-Thinking-2507Alibaba
0.31
$0.30 / $3
311 Gemini 3.7 Flash (low reasoning)Google
0.31
$1.50 / $7.50
311 Kimi K2 (0905)Moonshot AI
0.31
$0.60 / $2.50
311 Qwen3-32B (reasoning on)Alibaba
0.31
$0.14 / $0.40
311 Qwen3-Coder-30B-A3B-InstructAlibaba
0.31
$0.07 / $0.28
311 Qwen3-Next-80B-A3B-InstructAlibaba
0.31
$0.10 / $1.10
311 GLM-4.5-Air (no reasoning)Z.ai
0.31
$0.14 / $0.86
311 Qwen3.5-4B (reasoning by prefill)Alibaba
0.31
–
311 Qwen3.5-9B (reasoning by prefill)Alibaba
0.31
$0.10 / $0.15
311 Qwen3.6-27B (reasoning by prefill)Alibaba
0.31
$0.30 / $3.20
311 o3 (high reasoning)OpenAI
0.31
$2 / $8
335 Gemini 3.6 Flash (minimal reasoning)Google
0.30
$1.50 / $7.50
335 Qwen2.5-32B-InstructAlibaba
0.30
–
335 Gemma 2 27BGoogle
0.30
$0.65 / $0.65
335 Gemma 4 E4B (reasoning by prefill)Google
0.30
–
335 QwQ-32BAlibaba
0.30
–
335 Magistral Small 1.2 (reasoning by system prompt)Mistral AI
0.30
–
335 Qwen2.5-VL-3B-InstructAlibaba
0.30
–
335 DeepSeek-R1DeepSeek
0.30
$0.70 / $2.50
335 InternLM3 8B InstructShanghai AI Lab
0.30
–
335 Qwen2.5-1.5B-InstructAlibaba
0.30
–
335 Inflection 3 ProductivityInflection AI
0.30
–
335 gpt-oss-20b (low reasoning)OpenAI
0.30
$0.03 / $0.15
335 Gemma 2 2BGoogle
0.30
–
335 Gemma 2 9BGoogle
0.30
–
335 Olmo 3 7B InstructAi2
0.30
–
350 Gemma 4 E4BGoogle
0.29
–
350 Qwen3-Omni-30B-A3B-ThinkingAlibaba
0.29
–
350 Gemma 3 12BGoogle
0.29
$0.05 / $0.15
350 Gemma 3 27BGoogle
0.29
$0.12 / $0.20
350 Gemma 3 4BGoogle
0.29
$0.05 / $0.10
350 Olmo 3 7B ThinkAi2
0.29
–
350 o3 (medium reasoning)OpenAI
0.29
$2 / $8
350 Qwen3.5-2B (no reasoning)Alibaba
0.29
–
350 Qwen3-VL-4B-InstructAlibaba
0.29
–
350 Mistral Small 4 (no reasoning)Mistral AI
0.29
$0.15 / $0.60
350 Qwen2.5-14B-InstructAlibaba
0.29
–
350 Kimi K2 (0711)Moonshot AI
0.29
$0.57 / $2.30
350 gpt-oss-120b (medium reasoning)OpenAI
0.29
$0.15 / $0.60
350 Qwen3-Next-80B-A3B-ThinkingAlibaba
0.29
$0.15 / $1.20
364 Nemotron 3 Nano 30B A3BNVIDIA
0.28
$0.05 / $0.20
364 o3 (low reasoning)OpenAI
0.28
$2 / $8
364 Qwen3.5-35B-A3B (reasoning by prefill)Alibaba
0.28
$0.16 / $1.30
364 Nanbeige4-3B-Thinking (2510)Nanbeige
0.28
–
364 Solar 10.7B Instruct v1.0Upstage
0.28
–
364 Qwen3-4B-Thinking-2507Alibaba
0.28
–
364 Qwen3.6-35B-A3B (reasoning by prefill)Alibaba
0.28
$0.10 / $1
364 Qwen3-VL-2B-InstructAlibaba
0.28
–
364 LFM2-8B-A1BLiquid AI
0.28
–
373 LFM2-24B-A2BLiquid AI
0.27
–
373 Nemotron Nano 12B v2 VL (BF16, no reasoning)NVIDIA
0.27
–
373 gpt-oss-20b (high reasoning)OpenAI
0.27
$0.03 / $0.15
376 Nemotron Nano 12B v2 VL (BF16)NVIDIA
0.26
–
376 Nanbeige4-3B-Thinking (2511)Nanbeige
0.26
–
378 Qwen3-0.6B (reasoning on)Alibaba
0.25
–
378 Nemotron 3 Nano 30B A3B (reasoning by prefill)NVIDIA
0.25
$0.05 / $0.20

Swipe the table sideways for more columns.

Ranks follow the score as shown, so equal numbers share a rank. Results as published by UGI Leaderboard; we do not re-run them.

What it measures

How closely the model matches the writing style of a given example.

What it does not measure

Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.

Source

UGI Leaderboard · Methodology

947 results from UGI Leaderboard not ranked here · show why

We rank a result only when we can tie it to a specific model you can use. These are left out:

  • Community fine-tunes and merges: 934
  • No score published: 13

UGI Leaderboard by DontPlanToEnd, Apache License 2.0.