LLM Optimizer

予算に合った最も賢いモデルを見つけよう

Artificial Analysis より 5時間 57分前 に更新 · 664 モデル

モデル 開発元 知能 コーディング 入力 $/M 出力 $/M 混合 $/M 速度 t/s TTFT s コンテキスト 価値 ↓
Agnes 3.0 Flash Sapiens AI 35.5 — $0.05 $0.15 $0.07 0.0 0.00 — 473.3
Llama 3.1 Instruct 8B Meta 6.9 5.4 $0.02 $0.05 $0.03 0.0 0.00 — 246.4
Agnes 2.5 Pro Beta Sapiens AI 35.2 62.3 $0.10 $0.30 $0.15 0.0 0.00 — 234.7
Hy3-preview (Reasoning) Tencent 22.7 — $0.06 $0.21 $0.10 0.0 0.00 — 227.0
Ling 3.0 Flash InclusionAI 24.9 50.6 $0.07 $0.22 $0.11 362.3 1.73 — 224.3
Gemma 4 E4B (Reasoning) Google 8.9 9.4 $0.02 $0.10 $0.04 52.0 0.35 — 222.5
Ling-3.0-flash-VL InclusionAI 24.6 57.0 $0.07 $0.22 $0.11 148.6 1.24 — 221.6
Qwen3.5 4B (Reasoning) Alibaba 13.1 22.6 $0.03 $0.15 $0.06 20.2 0.51 — 218.3
Ling-3.0-flash-Fin InclusionAI 22.6 55.6 $0.07 $0.22 $0.11 163.8 1.46 — 203.6
Gemma 4 E4B (Non-reasoning) Google 7.5 — $0.02 $0.10 $0.04 53.3 0.32 — 187.5
GPT-6 Luna (max) OpenAI 37.3 — $0.10 $0.50 $0.20 154.5 72.25 — 186.5
Qwen3.5 4B (Non-reasoning) Alibaba 10.8 20.3 $0.03 $0.15 $0.06 16.6 0.54 — 180.0
GLM 5.3 Flash Z AI 41.8 71.5 $0.15 $0.50 $0.24 51.6 3.23 — 176.4
Granite 4.2 3B IBM 9.1 17.5 $0.03 $0.12 $0.05 232.8 0.27 — 175.0
Qwen3.8-Flash-Next Alibaba 39.8 73.1 $0.15 $0.47 $0.23 53.2 1.38 — 173.0
Hy3-preview (Non-reasoning) Tencent 17.0 — $0.06 $0.21 $0.10 0.0 0.00 — 170.0
GPT-6 Luna (xhigh) OpenAI 33.9 — $0.10 $0.50 $0.20 137.3 14.42 — 169.5
GPT-6 Luna (high) OpenAI 32.1 — $0.10 $0.50 $0.20 153.9 10.66 — 160.5
DeepSeek V4 Flash 0420 (Non-reasoning) DeepSeek 18.9 — $0.09 $0.20 $0.12 0.0 0.00 — 158.8
DeepSeek V4 Flash 0420 (Reasoning, High Effort) DeepSeek 26.0 52.0 $0.13 $0.28 $0.17 0.0 0.00 — 154.8
GPT-6 Luna (medium) OpenAI 29.5 — $0.10 $0.50 $0.20 170.3 3.06 — 147.5
DeepSeek V4 Flash 0420 (Reasoning, Max Effort) DeepSeek 24.2 56.2 $0.13 $0.28 $0.17 0.0 0.00 — 144.0
MiMo-V2.5 Xiaomi 25.2 56.8 $0.14 $0.28 $0.17 36.5 1.88 — 144.0
Sarvam 30B (high) Sarvam 6.6 — $0.03 $0.11 $0.05 0.0 0.00 — 140.4
MiMo-V2-Flash (Reasoning) Xiaomi 20.8 — $0.10 $0.30 $0.15 0.0 0.00 — 138.7
Nemotron 3.5 Lightning NVIDIA 12.9 26.8 $0.07 $0.22 $0.11 267.8 0.46 — 119.4
Sarvam 105B (high) Sarvam 8.8 — $0.04 $0.17 $0.07 0.0 0.00 — 118.9
Step 3.5 Flash 2603 StepFun 17.0 — $0.10 $0.30 $0.15 0.0 0.00 — 113.3
Step 3.5 Flash StepFun 16.6 — $0.10 $0.30 $0.15 0.0 0.00 — 110.7
NVIDIA Nemotron Nano 9B V2 (Reasoning) NVIDIA 7.4 — $0.04 $0.16 $0.07 97.4 2.25 — 105.7
Granite 4.1 8B IBM 6.6 9.5 $0.05 $0.10 $0.06 0.0 0.00 — 104.8
GPT-6 Luna (low) OpenAI 20.9 — $0.10 $0.50 $0.20 144.6 1.65 — 104.5
Granite 4.2 8B IBM 11.1 22.4 $0.06 $0.25 $0.11 114.3 0.33 — 103.7
Hy3 Tencent 25.3 58.8 $0.14 $0.58 $0.25 92.8 1.69 — 101.2
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) NVIDIA 8.9 14.4 $0.05 $0.20 $0.09 147.6 0.74 — 101.1
GLM-4.7-Flash (Reasoning) Z AI 14.9 — $0.07 $0.40 $0.15 0.0 0.00 — 97.4
Nova Micro Amazon 5.9 — $0.04 $0.14 $0.06 257.1 0.58 — 96.7
Gemma 4 12B (Reasoning) Google 14.2 31.0 $0.10 $0.30 $0.15 138.3 1.31 — 94.7
gpt-oss-20b (low) OpenAI 10.0 — $0.07 $0.21 $0.11 239.8 0.52 — 94.3
GPT-5 nano (high) OpenAI 13.0 — $0.05 $0.40 $0.14 0.0 0.00 — 94.2
Gemma 4 26B A4B (Reasoning) Google 16.7 39.3 $0.12 $0.37 $0.18 0.0 0.00 — 93.3
gpt-oss-20b (high) OpenAI 9.0 20.7 $0.07 $0.18 $0.10 178.9 0.45 — 91.8
GPT-6 Luna (Non-reasoning) OpenAI 18.3 — $0.10 $0.50 $0.20 143.6 0.69 — 91.5
Qwen3.5 9B (Reasoning) Alibaba 13.7 28.7 $0.14 $0.20 $0.15 71.2 0.77 — 90.7
GPT-5 nano (medium) OpenAI 12.5 — $0.05 $0.40 $0.14 0.0 0.00 — 90.6
MiMo-V2.6-Pro Xiaomi 46.3 — $0.43 $0.87 $0.54 54.2 1.42 — 85.1
GPT-5.6 Luna (max) OpenAI 37.3 71.4 $0.20 $1.20 $0.45 143.4 87.77 — 82.9
NVIDIA Nemotron Nano 9B V2 (Non-reasoning) NVIDIA 6.8 — $0.05 $0.20 $0.09 162.3 1.14 — 79.1
NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) NVIDIA 6.8 — $0.05 $0.20 $0.09 173.7 0.43 — 77.3
GPT-5.6 Luna (xhigh) OpenAI 34.6 68.6 $0.20 $1.20 $0.45 136.5 26.92 — 76.9
DeepSeek V4.1 Flash (Reasoning, Max Effort) DeepSeek 39.5 — $0.30 $1.20 $0.53 230.9 0.79 — 75.2
Qwen2.5 Turbo Alibaba 6.4 — $0.05 $0.20 $0.09 0.0 0.00 — 72.7
GPT-5.6 Luna (high) OpenAI 32.1 63.3 $0.20 $1.20 $0.45 133.0 9.98 — 71.3
Qwen3.5 9B (Non-reasoning) Alibaba 13.3 23.5 $0.17 $0.25 $0.19 94.7 0.45 — 70.0
GLM-4.7-Flash (Non-reasoning) Z AI 10.6 — $0.07 $0.40 $0.15 0.0 0.00 — 69.3
Llama 3 Instruct 8B Meta 4.8 — $0.04 $0.14 $0.07 0.0 0.00 — 68.6
DeepSeek V3.2 (Reasoning) DeepSeek 21.5 44.2 $0.28 $0.42 $0.32 0.0 0.00 — 68.3
Gemma 4 31B (Non-reasoning) Google 13.9 33.2 $0.14 $0.40 $0.20 39.1 0.97 — 67.8
Gemma 4 26B A4B (Non-reasoning) Google 13.1 — $0.13 $0.40 $0.20 70.2 0.80 — 66.2
Grok 4 Fast (Reasoning) SpaceXAI 17.9 — $0.20 $0.50 $0.28 0.0 0.00 — 65.1
Nova Lite Amazon 6.7 — $0.06 $0.24 $0.10 0.0 0.00 — 63.8
Gemma 4 12B (Non-reasoning) Google 9.4 — $0.10 $0.30 $0.15 141.8 1.40 — 62.7
Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) Google 10.4 — $0.10 $0.40 $0.17 0.0 0.00 — 59.4
Granite 3.3 8B (Non-reasoning) IBM 4.9 — $0.03 $0.25 $0.09 0.0 0.00 — 57.6
Llama 2 Chat 7B Meta 5.7 — $0.05 $0.25 $0.10 0.0 0.00 — 57.0
Granite 4.0 H Small IBM 6.0 — $0.06 $0.25 $0.11 12.5 35.48 — 56.1
DeepSeek V4 Pro 0424 (Reasoning, Max Effort) DeepSeek 30.4 59.4 $0.43 $0.87 $0.54 0.0 0.00 — 55.9
MiniMax-M3 MiniMax 29.2 58.6 $0.30 $1.20 $0.53 159.3 0.77 — 55.6
GPT-5.6 Luna (medium) OpenAI 25.0 50.7 $0.20 $1.20 $0.45 133.6 1.92 — 55.6
DeepSeek V4 Pro 0424 (Reasoning, High Effort) DeepSeek 30.1 58.7 $0.43 $0.87 $0.54 0.0 0.00 — 55.3
Mistral Small 3.2 Mistral 8.2 12.5 $0.10 $0.30 $0.15 0.0 0.00 — 54.7
Solar Pro 4 Upstage 28.2 52.7 $0.30 $1.20 $0.53 52.5 1.19 — 53.7
Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) Google 9.3 — $0.10 $0.40 $0.17 0.0 0.00 — 53.1
Inkling Small Thinking Machines 27.8 52.9 $0.30 $1.20 $0.53 219.4 1.75 — 53.0
DeepSeek V4 Flash Vision (Reasoning, Max Effort) DeepSeek 34.8 65.0 $0.44 $1.32 $0.66 237.2 0.88 — 52.7
DeepSeek V3.2 Exp (Reasoning) DeepSeek 16.6 — $0.28 $0.42 $0.32 0.0 0.00 — 52.7
Granite 4.2 30B IBM 14.8 29.9 $0.16 $0.65 $0.28 67.0 0.26 — 52.5
DeepSeek V4 Flash 0731 (Reasoning, Max Effort) DeepSeek 34.3 69.1 $0.44 $1.32 $0.66 0.0 0.00 — 52.0
GPT-5 nano (minimal) OpenAI 7.1 — $0.05 $0.40 $0.14 0.0 0.00 — 51.4
DeepSeek V3.2 (Non-reasoning) DeepSeek 16.0 — $0.28 $0.42 $0.32 0.0 0.00 — 50.8
Gemini 2.5 Flash-Lite (Reasoning) Google 8.5 — $0.10 $0.40 $0.17 0.0 0.00 — 48.6
Ministral 3 3B Mistral 4.8 4.8 $0.10 $0.10 $0.10 243.8 0.48 — 48.0
MiMo-V2.5-Pro Xiaomi 26.0 60.2 $0.43 $0.87 $0.54 49.7 2.97 — 47.8
Agnes 2.5 Pro Alpha (based on Qwen3.5 397B A17B) Sapiens AI 26.8 58.8 $0.45 $0.90 $0.56 201.9 2.97 — 47.6
Mistral Small 3.1 Mistral 7.1 26.3 $0.10 $0.30 $0.15 0.0 0.00 — 47.3
GPT-5.6 Luna (low) OpenAI 21.0 44.2 $0.20 $1.20 $0.45 135.2 1.32 — 46.7
Qwen3.5 Omni Flash Alibaba 12.5 — $0.10 $0.80 $0.28 240.2 1.08 — 45.5
GPT-5.4 nano (xhigh) OpenAI 20.7 56.1 $0.20 $1.25 $0.46 0.0 0.00 — 44.7
Mistral Small 3 Mistral 6.7 — $0.10 $0.30 $0.15 0.0 0.00 — 44.7
GPT-4.1 nano OpenAI 7.8 11.1 $0.10 $0.40 $0.17 0.0 0.00 — 44.6
Step 3.7 Flash StepFun 19.5 39.6 $0.20 $1.15 $0.44 201.4 1.43 — 44.5
gpt-oss-120b (high) OpenAI 11.6 30.4 $0.15 $0.59 $0.26 202.0 0.52 — 44.4
DeepSeek V3.2 Exp (Non-reasoning) DeepSeek 13.9 — $0.28 $0.42 $0.32 0.0 0.00 — 44.1
MiniMax-M2.5 MiniMax 22.8 — $0.30 $1.20 $0.53 0.0 0.00 — 43.4
MiniMax-M2.7 MiniMax 22.8 52.6 $0.30 $1.20 $0.53 0.0 0.00 — 43.4
GPT-5.4 nano (medium) OpenAI 20.0 — $0.20 $1.25 $0.46 0.0 0.00 — 43.2
Mistral Small 4 (Reasoning) Mistral 11.3 26.6 $0.15 $0.60 $0.26 168.0 0.51 — 43.1
Solar Mini Upstage 6.4 — $0.15 $0.15 $0.15 0.0 0.00 — 42.7
Qwen3 VL 32B (Reasoning) Alibaba 11.9 — $0.16 $0.64 $0.28 0.0 0.00 — 42.5
Grok 3 mini Reasoning (high) SpaceXAI 14.6 — $0.30 $0.50 $0.35 0.0 0.00 — 41.7
Olmo 3 7B Instruct Allen Institute for AI 5.2 — $0.10 $0.20 $0.13 0.0 0.00 — 41.6
KAT Coder Pro V2 KwaiKAT 21.7 59.5 $0.30 $1.20 $0.53 0.0 0.00 — 41.3
gpt-oss-120b (low) OpenAI 10.2 21.2 $0.15 $0.55 $0.25 190.6 0.49 — 41.0
Grok 4 Fast (Non-reasoning) SpaceXAI 11.1 — $0.20 $0.50 $0.28 0.0 0.00 — 40.4
Seed-OSS-36B-Instruct ByteDance Seed 12.1 — $0.21 $0.57 $0.30 0.0 0.00 — 40.3
MiniMax-M2.1 MiniMax 20.9 — $0.30 $1.20 $0.53 0.0 0.00 — 39.8
Apertus 8B Instruct Swiss AI Initiative 4.8 — $0.10 $0.20 $0.13 0.0 0.00 — 38.4
Gemini 2.5 Flash-Lite (Non-reasoning) Google 6.7 — $0.10 $0.40 $0.17 0.0 0.00 — 38.3
DeepSeek V4 Pro 0424 (Non-reasoning) DeepSeek 20.8 — $0.43 $0.87 $0.54 0.0 0.00 — 38.2
Mercury 2 Inception 13.8 31.1 $0.25 $0.75 $0.38 717.0 4.00 — 36.8
Ministral 3 8B Mistral 5.5 9.7 $0.15 $0.15 $0.15 94.6 0.52 — 36.7
LongCat 2.0 LongCat 19.1 45.3 $0.30 $1.20 $0.53 0.0 0.00 — 36.4
Qwen3.7 Plus Alibaba 25.2 55.9 $0.40 $1.60 $0.70 58.2 1.65 — 36.0
MiniMax-M2 MiniMax 18.6 — $0.30 $1.20 $0.53 0.0 0.00 — 35.4
GPT-5.6 Luna (Non-reasoning) OpenAI 15.5 39.3 $0.20 $1.20 $0.45 125.5 0.67 — 34.4
Mistral Small 4 (Non-reasoning) Mistral 9.0 — $0.15 $0.60 $0.26 157.0 0.52 — 34.4
MiMo-V2.5-Pro (Non-reasoning) Xiaomi 18.3 — $0.43 $0.87 $0.54 46.1 3.58 — 33.6
Ling-flash-2.0 InclusionAI 7.8 — $0.14 $0.57 $0.25 0.0 0.00 — 31.6
Apodex 1.1 Apodex 30.4 60.8 $0.30 $3.00 $0.97 0.0 0.00 — 31.2
Qwen3 32B (Reasoning) Alibaba 8.6 15.3 $0.16 $0.64 $0.28 0.0 0.00 — 30.7
DeepSeek V3.1 Terminus (Non-reasoning) DeepSeek 13.9 — $0.27 $1.00 $0.45 0.0 0.00 — 30.7
Step 5 Preview StepFun 43.7 — $1.00 $2.70 $1.43 75.0 2.94 — 30.7
Qwen3 VL 32B Instruct Alibaba 8.4 — $0.16 $0.64 $0.28 0.0 0.00 — 30.0
Ministral 3 14B Mistral 6.0 14.4 $0.20 $0.20 $0.20 91.2 0.60 — 30.0
Qwen3.8 27B (xhigh) Alibaba 33.7 68.1 $0.50 $3.00 $1.13 44.5 1.27 — 30.0
GPT-5 mini (medium) OpenAI 20.6 — $0.25 $2.00 $0.69 0.0 0.00 — 29.9
GLM-4.5-Air Z AI 11.1 — $0.17 $0.98 $0.37 0.0 0.00 — 29.8
Qwen3 235B A22B 2507 Instruct Alibaba 12.0 — $0.23 $0.92 $0.40 0.0 0.00 — 29.8
Solar Pro 3 Upstage 7.8 16.2 $0.15 $0.60 $0.26 0.0 0.00 — 29.8
Quasar 438B (max, based on GLM-5.2) Multiverse Computing 26.7 61.2 $0.60 $1.80 $0.90 152.2 0.57 — 29.7
GPT-5.1 Codex mini (high) OpenAI 20.4 — $0.25 $2.00 $0.69 0.0 0.00 — 29.7
Ring-flash-2.0 InclusionAI 7.2 — $0.14 $0.57 $0.25 0.0 0.00 — 29.1
Nemotron 3 Super 120B A12B (Reasoning) NVIDIA 12.8 37.7 $0.30 $0.90 $0.45 163.4 1.04 — 28.4
Qwen3.5 35B A3B (Reasoning) Alibaba 19.3 — $0.25 $2.00 $0.69 0.0 0.00 — 28.1
Qwen3.5 27B (Reasoning) Alibaba 22.9 — $0.30 $2.40 $0.82 0.0 0.00 — 27.8
Gemini 3.1 Flash-Lite Google 15.6 34.7 $0.25 $1.50 $0.56 0.0 0.00 — 27.7
Muse Glimmer (high) Meta 17.5 49.0 $0.35 $1.50 $0.64 93.6 0.36 — 27.5
Gemini 3.8 Flash (high) Google 40.9 76.3 $0.75 $3.75 $1.50 300.8 10.74 — 27.3
Qwen3 Next 80B A3B (Reasoning) Alibaba 11.2 17.4 $0.15 $1.20 $0.41 165.6 1.20 — 27.2
Phi-4 Microsoft 5.9 — $0.13 $0.50 $0.22 39.3 1.01 — 26.9
Gemini 3.8 Flash (medium) Google 39.8 74.1 $0.75 $3.75 $1.50 0.0 0.00 — 26.5
Gemini 3.7 Flash (medium) Google 39.6 71.5 $0.75 $3.75 $1.50 0.0 0.00 — 26.4
Trinity Large Thinking Arcee AI 10.8 25.8 $0.25 $0.90 $0.41 368.0 1.14 — 26.2
Gemini 3.5 Flash-Lite Google 22.2 49.3 $0.30 $2.50 $0.85 350.4 6.84 — 26.1
Qwen3 32B (Non-reasoning) Alibaba 7.3 — $0.16 $0.64 $0.28 0.0 0.00 — 26.1
Gemini 3.7 Flash (high) Google 39.1 76.1 $0.75 $3.75 $1.50 0.0 0.00 — 26.1
Llama 4 Scout Meta 8.1 8.2 $0.19 $0.68 $0.31 103.9 0.61 — 25.9
GPT-4o mini OpenAI 6.7 11.4 $0.15 $0.60 $0.26 0.0 0.00 — 25.6
GPT-5.4 nano (Non-Reasoning) OpenAI 11.7 — $0.20 $1.25 $0.46 0.0 0.00 — 25.3
NVIDIA Nemotron Nano 12B v2 VL (Reasoning) NVIDIA 7.5 — $0.20 $0.60 $0.30 41.9 13.27 — 25.0
GLM-4.6V (Reasoning) Z AI 11.2 — $0.30 $0.90 $0.45 0.0 0.00 — 24.9
Gemini 3.7 Flash (low) Google 36.9 71.0 $0.75 $3.75 $1.50 0.0 0.00 — 24.6
Qwen3.8 27B (medium) Alibaba 27.6 56.1 $0.50 $3.00 $1.13 48.3 1.20 — 24.5
Nemotron 3 Nano Omni 30B A3B Reasoning NVIDIA 10.3 13.8 $0.20 $1.09 $0.42 274.2 0.28 — 24.5
GPT-5 mini (high) OpenAI 16.8 15.6 $0.25 $2.00 $0.69 0.0 0.00 — 24.4
Muse Spark 1.3 (max) Meta 48.1 75.8 $1.25 $4.25 $2.00 220.3 25.29 — 24.1
Qwen3.6 Plus Alibaba 27.0 54.5 $0.50 $3.00 $1.13 0.0 0.00 — 24.0
Llama 4 Maverick Meta 10.0 16.3 $0.26 $0.91 $0.42 108.3 0.58 — 23.7
Qwen3 VL 8B Instruct Alibaba 7.3 — $0.18 $0.70 $0.31 0.0 0.00 — 23.5
Qwen3.5 27B (Non-reasoning) Alibaba 19.4 — $0.30 $2.40 $0.82 0.0 0.00 — 23.5
Gemini 3 Flash Preview (Reasoning) Google 26.3 — $0.50 $3.00 $1.13 0.0 0.00 — 23.4
Qwen3 Next 80B A3B Instruct Alibaba 9.6 — $0.15 $1.20 $0.41 166.8 1.06 — 23.3
Qwen3.8 27B (low) Alibaba 26.2 58.2 $0.50 $3.00 $1.13 51.3 1.30 — 23.3
Gemini 3.6 Flash (high) Google 34.0 69.2 $0.75 $3.75 $1.50 0.0 0.00 — 22.7
Qwen3 VL 30B A3B Instruct Alibaba 7.9 — $0.20 $0.80 $0.35 0.0 0.00 — 22.6
Muse Spark 1.3 (xhigh) Meta 45.1 76.5 $1.25 $4.25 $2.00 247.0 22.08 — 22.6
Llama Nemotron Super 49B v1.5 (Reasoning) NVIDIA 9.0 — $0.40 $0.40 $0.40 38.8 5.38 — 22.5
Gemini 3.8 Flash (low) Google 33.5 73.5 $0.75 $3.75 $1.50 0.0 0.00 — 22.3
GLM-4.7 (Reasoning) Z AI 22.2 45.3 $0.60 $2.20 $1.00 0.0 0.00 — 22.2
Qwen3.5 35B A3B (Non-reasoning) Alibaba 15.1 37.0 $0.25 $2.00 $0.69 0.0 0.00 — 21.9
Grok Build 0.1 0616 SpaceXAI 27.2 51.5 $1.00 $2.00 $1.25 0.0 0.00 — 21.8
Qwen3.6 35B A3B (Reasoning) Alibaba 18.2 41.9 $0.38 $2.25 $0.84 126.2 1.13 — 21.6
Qwen3 30B A3B 2507 Instruct Alibaba 7.5 — $0.20 $0.80 $0.35 0.0 0.00 — 21.4
Nemotron 3 Ultra 550B A55B (Reasoning) NVIDIA 22.9 49.3 $0.60 $2.50 $1.07 162.1 1.46 — 21.3
Mistral Small (Feb '24) Mistral 5.5 — $0.15 $0.60 $0.26 0.0 0.00 — 21.0
GLM-5.3 (max) Z AI 44.8 74.8 $1.40 $4.40 $2.15 63.2 3.57 — 20.8
Jamba 1.5 Mini AI21 Labs 5.2 — $0.20 $0.40 $0.25 0.0 0.00 — 20.8
Kimi K2.5 (Reasoning) Kimi 23.5 46.8 $0.60 $2.75 $1.14 0.0 0.00 — 20.7
Kimi K2 Thinking Kimi 22.0 — $0.60 $2.50 $1.07 0.0 0.00 — 20.5
Ling-2.6-1T InclusionAI 17.0 — $0.30 $2.50 $0.85 0.0 0.00 — 20.0
Mistral 7B Instruct Mistral 5.0 — $0.25 $0.25 $0.25 0.0 0.00 — 20.0
Muse Spark 1.2 (xhigh) Meta 39.6 72.2 $1.25 $4.25 $2.00 0.0 0.00 — 19.8
Ring-2.6-1T InclusionAI 16.6 42.8 $0.30 $2.50 $0.85 122.5 2.06 — 19.5
Celeris-1 Celeris 6.3 14.4 $0.20 $0.70 $0.33 1956.0 0.48 — 19.4
Qwen3 8B (Non-reasoning) Alibaba 6.0 — $0.18 $0.70 $0.31 0.0 0.00 — 19.4
Mistral Small (Sep '24) Mistral 5.8 — $0.20 $0.60 $0.30 0.0 0.00 — 19.3
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) NVIDIA 5.8 — $0.20 $0.60 $0.30 187.8 1.86 — 19.3
GLM-4.6 (Reasoning) Z AI 18.5 45.8 $0.55 $2.20 $0.96 0.0 0.00 — 19.2
Qwen3 30B A3B (Non-reasoning) Alibaba 6.6 — $0.20 $0.80 $0.35 0.0 0.00 — 18.9
GLM-4.6V (Non-reasoning) Z AI 8.4 — $0.30 $0.90 $0.45 0.0 0.00 — 18.7
Llama Nemotron Super 49B v1.5 (Non-reasoning) NVIDIA 7.4 — $0.40 $0.40 $0.40 45.7 5.61 — 18.5
DeepSeek V3 (Dec '24) DeepSeek 8.5 23.0 $0.32 $0.89 $0.46 0.0 0.00 — 18.4
Reka Flash (Sep '24) Reka AI 6.4 — $0.20 $0.80 $0.35 0.0 0.00 — 18.3
DeepSeek V4 Pro 0813 (Reasoning, Max Effort) DeepSeek 36.0 68.8 $1.32 $3.96 $1.98 78.6 1.16 — 18.2
Qwen3 Omni 30B A3B (Reasoning) Alibaba 7.8 — $0.25 $0.97 $0.43 111.1 0.96 — 18.1
Qwen3.6 35B A3B (Non-reasoning) Alibaba 15.2 28.1 $0.38 $2.25 $0.84 132.8 1.18 — 18.0
GLM-5 (Reasoning) Z AI 27.9 — $1.00 $3.20 $1.55 0.0 0.00 — 18.0
Qwen3.8 27B (Non-reasoning) Alibaba 20.2 44.6 $0.50 $3.00 $1.13 49.4 1.29 — 18.0
GLM-4.7 (Non-reasoning) Z AI 17.4 — $0.60 $2.20 $1.00 0.0 0.00 — 17.4
Qwen3 235B A22B 2507 (Reasoning) Alibaba 12.7 22.1 $0.23 $2.30 $0.75 0.0 0.00 — 17.0
Muse Spark 1.1 (xhigh) Meta 33.7 71.3 $1.25 $4.25 $2.00 0.0 0.00 — 16.9
Grok 4.20 0309 v2 (Reasoning) SpaceXAI 25.7 — $1.25 $2.50 $1.56 0.0 0.00 — 16.4
Qwen3 Coder Next Alibaba 9.2 36.2 $0.35 $1.20 $0.56 105.5 0.87 — 16.3
Kimi K2.5 (Non-reasoning) Kimi 19.4 — $0.60 $3.00 $1.20 0.0 0.00 — 16.2
DeepSeek V3.1 (Non-reasoning) DeepSeek 13.7 — $0.57 $1.68 $0.85 0.0 0.00 — 16.2
Qwen3.5 122B A10B (Non-reasoning) Alibaba 17.7 43.3 $0.40 $3.20 $1.10 144.3 1.01 — 16.1
Qwen2.5 Instruct 72B Alibaba 7.7 — $0.47 $0.49 $0.48 0.0 0.00 — 16.0
Nova 2.0 Omni (medium) Amazon 13.6 — $0.30 $2.50 $0.85 0.0 0.00 — 16.0
Reka Flash 3 Reka AI 5.6 — $0.20 $0.80 $0.35 96.8 0.99 — 16.0
Grok 4.3 (high) SpaceXAI 24.9 42.2 $1.25 $2.50 $1.56 0.0 0.00 — 15.9
Gemini 3 Flash Preview (Non-reasoning) Google 17.9 — $0.50 $3.00 $1.13 0.0 0.00 — 15.9
Grok 4.3 (medium) SpaceXAI 24.8 — $1.25 $2.50 $1.56 0.0 0.00 — 15.9
Qwen3.5 397B A17B (Non-reasoning) Alibaba 21.4 — $0.60 $3.60 $1.35 83.1 1.60 — 15.9
Qwen3.6 27B (Reasoning) Alibaba 21.4 53.7 $0.60 $3.60 $1.35 0.0 0.00 — 15.9
Kimi K2.6 Kimi 27.0 61.8 $0.95 $4.00 $1.71 0.0 0.00 — 15.8
Nova 2.0 Lite (high) Amazon 13.4 23.0 $0.30 $2.50 $0.85 191.3 10.08 — 15.8
GLM-5.2 (max) Z AI 33.7 68.8 $1.40 $4.40 $2.15 0.0 0.00 — 15.7
Llama 3.2 Instruct 11B (Vision) Meta 5.4 — $0.34 $0.34 $0.34 14.5 0.63 — 15.7
DeepSeek V3.1 (Reasoning) DeepSeek 13.5 — $0.59 $1.69 $0.86 0.0 0.00 — 15.6
Grok 4.3 (low) SpaceXAI 24.3 — $1.25 $2.50 $1.56 0.0 0.00 — 15.5
Grok 4.7 (xhigh) SpaceXAI 46.4 — $2.00 $6.00 $3.00 50.4 0.70 — 15.5
ERNIE 4.5 300B A47B Baidu 7.5 — $0.28 $1.10 $0.48 0.0 0.00 — 15.5
Grok 4.7 (high) SpaceXAI 46.3 — $2.00 $6.00 $3.00 39.6 0.73 — 15.4
Gemini 2.5 Flash (Reasoning) Google 13.1 — $0.30 $2.50 $0.85 0.0 0.00 — 15.4
GLM-4.6 (Non-reasoning) Z AI 14.9 — $0.57 $2.20 $0.98 0.0 0.00 — 15.2
Qwen3.8 Max (0902) Alibaba 45.4 76.2 $2.00 $6.00 $3.00 41.6 2.00 — 15.1
Kimi K2.7 Code Kimi 25.8 60.8 $0.95 $4.00 $1.71 50.7 1.27 — 15.1
Grok 4.6 (high) SpaceXAI 44.3 76.8 $2.00 $6.00 $3.00 70.3 38.52 — 14.8
Grok 4.6 (xhigh) SpaceXAI 44.2 75.9 $2.00 $6.00 $3.00 59.8 33.84 — 14.7
Nova 2.0 Lite (medium) Amazon 12.5 — $0.30 $2.50 $0.85 180.1 11.22 — 14.7
Qwen3.6 27B (Non-reasoning) Alibaba 19.8 46.6 $0.60 $3.60 $1.35 0.0 0.00 — 14.7
GPT-4.1 mini OpenAI 10.2 20.2 $0.40 $1.60 $0.70 0.0 0.00 — 14.6
GPT-5 mini (minimal) OpenAI 9.9 — $0.25 $2.00 $0.69 0.0 0.00 — 14.4
GPT-5.4 mini (xhigh) OpenAI 24.1 56.1 $0.75 $4.50 $1.69 0.0 0.00 — 14.3
Grok 4.6 (medium) SpaceXAI 42.8 74.4 $2.00 $6.00 $3.00 65.1 20.47 — 14.3
Kimi K2 0905 Kimi 15.3 — $0.60 $2.50 $1.07 0.0 0.00 — 14.2
Inkling (xhigh) Thinking Machines 25.0 52.1 $1.00 $4.05 $1.76 103.7 2.80 — 14.2
Qwen3.5 122B A10B (Reasoning) Alibaba 15.6 45.7 $0.40 $3.20 $1.10 132.6 1.02 — 14.2
Qwen3 VL 235B A22B Instruct Alibaba 9.9 — $0.40 $1.60 $0.70 0.0 0.00 — 14.1
GLM-5 (Non-reasoning) Z AI 21.8 — $1.00 $3.20 $1.55 0.0 0.00 — 14.1
Qwen3 Omni 30B A3B Instruct Alibaba 6.0 — $0.25 $0.97 $0.43 106.8 0.92 — 14.0
Nova 2.0 Lite (low) Amazon 11.8 — $0.30 $2.50 $0.85 198.4 4.52 — 13.9
Kimi K2.6 (Non-reasoning) Kimi 23.6 — $0.95 $4.00 $1.71 0.0 0.00 — 13.8
Qwen3.5 397B A17B (Reasoning) Alibaba 18.4 48.2 $0.60 $3.60 $1.35 85.4 1.64 — 13.6
Qwen3.5 Omni Plus Alibaba 20.4 — $0.40 $4.80 $1.50 76.6 1.18 — 13.6
Qwen3.8 Max Alibaba 40.2 71.8 $2.00 $6.00 $3.00 0.0 0.00 — 13.4
Qwen3.8 2.4T A95B Alibaba 39.9 71.9 $2.00 $6.00 $3.00 40.7 2.05 — 13.3
GLM-5.1 (Reasoning) Z AI 26.1 55.8 $1.28 $4.07 $1.98 0.0 0.00 — 13.2
Qwen3 30B A3B 2507 (Reasoning) Alibaba 9.8 12.1 $0.20 $2.40 $0.75 0.0 0.00 — 13.1
Nova 2.0 Omni (low) Amazon 11.1 — $0.30 $2.50 $0.85 0.0 0.00 — 13.1
Grok 4.5 (high) SpaceXAI 38.8 72.4 $2.00 $6.00 $3.00 0.0 0.00 — 12.9
QwQ 32B Alibaba 9.5 — $0.66 $1.00 $0.74 0.0 0.00 — 12.8
Kimi K2 Kimi 12.7 — $0.57 $2.30 $1.00 0.0 0.00 — 12.7
Qwen3 VL 30B A3B (Reasoning) Alibaba 9.5 — $0.20 $2.40 $0.75 0.0 0.00 — 12.7
Qwen3 VL 8B (Reasoning) Alibaba 8.2 — $0.18 $2.10 $0.66 0.0 0.00 — 12.4
Mistral Large 3 Mistral 9.3 20.1 $0.50 $1.50 $0.75 78.1 0.76 — 12.4
MiniMax M1 80k MiniMax 11.7 — $0.55 $2.20 $0.96 0.0 0.00 — 12.1
GPT-6 Sol (max) OpenAI 47.5 — $2.00 $10.00 $4.00 116.3 97.42 — 11.9
Llama 3.1 Instruct 70B Meta 6.6 — $0.56 $0.56 $0.56 0.0 0.00 — 11.8
Grok 4.6 (low) SpaceXAI 35.1 66.3 $2.00 $6.00 $3.00 50.8 3.59 — 11.7
GPT-5.4 mini (medium) OpenAI 19.7 — $0.75 $4.50 $1.69 0.0 0.00 — 11.7
Gemini 2.5 Flash (Non-reasoning) Google 9.9 — $0.30 $2.50 $0.85 0.0 0.00 — 11.6
Mistral Medium 3.1 Mistral 9.2 20.5 $0.40 $2.00 $0.80 0.0 0.00 — 11.5
Magistral Small 1.2 Mistral 8.6 14.7 $0.50 $1.50 $0.75 0.0 0.00 — 11.5
GLM-5.1 (Non-reasoning) Z AI 24.2 — $1.38 $4.40 $2.13 0.0 0.00 — 11.3
Mistral Medium 3 Mistral 9.0 — $0.40 $2.00 $0.80 0.0 0.00 — 11.3
Claude 3 Haiku Anthropic 5.6 — $0.25 $1.25 $0.50 0.0 0.00 — 11.2
Qwen3 8B (Reasoning) Alibaba 7.3 9.0 $0.18 $2.10 $0.66 0.0 0.00 — 11.1
GPT-6 Sol (xhigh) OpenAI 44.1 — $2.00 $10.00 $4.00 115.7 26.11 — 11.0
Qwen3 14B (Non-reasoning) Alibaba 6.7 — $0.35 $1.40 $0.61 0.0 0.00 — 10.9
Llama 3.3 Instruct 70B Meta 7.7 11.9 $0.71 $0.72 $0.71 90.9 0.60 — 10.8
GPT-6 Sol (high) OpenAI 42.8 — $2.00 $10.00 $4.00 103.5 10.60 — 10.7
Qwen3 Coder 30B A3B Instruct Alibaba 9.6 — $0.45 $2.25 $0.90 0.0 0.00 — 10.7
DeepSeek V3 0324 DeepSeek 9.7 21.2 $0.84 $1.18 $0.93 0.0 0.00 — 10.5
GLM-5.2 (Non-reasoning) Z AI 22.4 46.5 $1.40 $4.40 $2.15 0.0 0.00 — 10.4
Qwen3 VL 235B A22B (Reasoning) Alibaba 13.4 — $0.40 $4.00 $1.30 0.0 0.00 — 10.3
Nova 2.0 Lite (Non-reasoning) Amazon 8.7 — $0.30 $2.50 $0.85 221.1 0.74 — 10.2
Qwen3 30B A3B (Reasoning) Alibaba 7.6 — $0.20 $2.40 $0.75 0.0 0.00 — 10.1
Mixtral 8x7B Instruct Mistral 5.1 — $0.45 $0.70 $0.51 0.0 0.00 — 10.0
Gemini 3.5 Flash (medium) Google 33.6 — $1.50 $9.00 $3.38 0.0 0.00 — 10.0
GPT-6 Sol (medium) OpenAI 39.8 — $2.00 $10.00 $4.00 134.4 6.70 — 9.9
DeepSeek R1 Distill Llama 70B DeepSeek 7.9 — $0.70 $1.10 $0.80 0.0 0.00 — 9.9
Qwen3.6 Max Preview Alibaba 28.4 — $1.30 $7.80 $2.92 0.0 0.00 — 9.7
Gemini 3.5 Flash (high) Google 32.6 70.1 $1.50 $9.00 $3.38 0.0 0.00 — 9.7
Nova 2.0 Omni (Non-reasoning) Amazon 8.2 — $0.30 $2.50 $0.85 0.0 0.00 — 9.6
Claude Sonnet 5 (Adaptive Reasoning, Max Effort) Anthropic 38.2 71.5 $2.00 $10.00 $4.00 81.9 86.67 — 9.6
GPT-5.6 Terra (max) OpenAI 42.1 76.7 $2.00 $12.00 $4.50 88.8 173.38 — 9.4
Grok 4.20 0309 v2 (Non-reasoning) SpaceXAI 14.2 — $1.25 $2.50 $1.56 0.0 0.00 — 9.1
Grok 4.3 (Non-reasoning) SpaceXAI 14.0 35.2 $1.25 $2.50 $1.56 0.0 0.00 — 9.0
o4-mini (high) OpenAI 16.7 — $1.10 $4.40 $1.93 0.0 0.00 — 8.7
Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort) Anthropic 34.4 — $2.00 $10.00 $4.00 71.4 12.02 — 8.6
Hermes 3 - Llama-3.1 70B Nous Research 6.0 — $0.70 $0.70 $0.70 0.0 0.00 — 8.6
GPT-6 Sol (low) OpenAI 33.9 — $2.00 $10.00 $4.00 105.9 1.64 — 8.5
Claude 4.5 Haiku (Reasoning) Anthropic 16.9 43.9 $1.00 $5.00 $2.00 154.6 13.92 — 8.4
GPT-5.6 Terra (xhigh) OpenAI 38.0 70.6 $2.00 $12.00 $4.50 80.1 8.52 — 8.4
GLM-4.5V (Reasoning) Z AI 7.6 — $0.60 $1.80 $0.90 0.0 0.00 — 8.4
Grok 4.20 0309 (Reasoning) SpaceXAI 25.2 — $2.00 $6.00 $3.00 0.0 0.00 — 8.4
Claude Sonnet 5 (Adaptive Reasoning, High Effort) Anthropic 31.7 — $2.00 $10.00 $4.00 62.9 1.91 — 7.9
Qwen3.7 Max Alibaba 29.5 66.0 $2.50 $7.50 $3.75 0.0 0.00 — 7.9
DeepSeek V3.1 Terminus (Reasoning) DeepSeek 14.8 43.5 $1.64 $2.75 $1.91 0.0 0.00 — 7.7
Claude 4.5 Haiku (Non-reasoning) Anthropic 15.4 — $1.00 $5.00 $2.00 94.9 0.53 — 7.7
GPT-5.6 Terra (high) OpenAI 34.2 67.1 $2.00 $12.00 $4.50 78.5 2.73 — 7.6
GLM-4.5V (Non-reasoning) Z AI 6.7 — $0.60 $1.80 $0.90 0.0 0.00 — 7.4
DeepSeek R1 0528 (May '25) DeepSeek 13.1 — $1.35 $3.00 $1.76 0.0 0.00 — 7.4
GPT-3.5 Turbo OpenAI 5.5 10.7 $0.50 $1.50 $0.75 0.0 0.00 — 7.3
Kimi K3 (max) Kimi 43.6 76.2 $3.00 $15.00 $6.00 37.7 3.32 — 7.3
GPT-5 Codex (high) OpenAI 24.9 — $1.25 $10.00 $3.44 0.0 0.00 — 7.2
Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback) Anthropic 57.6 — $4.00 $20.00 $8.00 0.0 0.00 — 7.2
GPT-5.1 (high) OpenAI 24.7 49.4 $1.25 $10.00 $3.44 0.0 0.00 — 7.2
Gemini 3.5 Flash (minimal) Google 23.8 — $1.50 $9.00 $3.38 0.0 0.00 — 7.1
GPT-6 Sol (Non-reasoning) OpenAI 28.1 — $2.00 $10.00 $4.00 100.3 0.74 — 7.0
Claude Sonnet 5 (Adaptive Reasoning, Medium Effort) Anthropic 28.1 — $2.00 $10.00 $4.00 65.5 1.13 — 7.0
Claude Opus 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback) Anthropic 56.0 — $4.00 $20.00 $8.00 83.0 63.68 — 7.0
GPT-5.4 (xhigh) OpenAI 39.0 71.1 $2.50 $15.00 $5.63 0.0 0.00 — 6.9
GPT-5.1 Codex (high) OpenAI 23.7 — $1.25 $10.00 $3.44 0.0 0.00 — 6.9
Qwen3 Max Thinking (Preview) Alibaba 16.3 — $1.20 $6.00 $2.40 0.0 0.00 — 6.8
Qwen3 235B A22B (Non-reasoning) Alibaba 8.3 — $0.70 $2.80 $1.23 0.0 0.00 — 6.8
GPT-5.3 Codex (xhigh) OpenAI 32.5 — $1.75 $14.00 $4.81 147.2 36.24 — 6.8
Claude Opus 5.5 (Adaptive Reasoning, High Effort, Default Fallback) Anthropic 53.6 — $4.00 $20.00 $8.00 71.7 19.08 — 6.7
GPT-5 (high) OpenAI 23.0 37.8 $1.25 $10.00 $3.44 0.0 0.00 — 6.7
GPT-5.6 Terra (medium) OpenAI 30.1 64.7 $2.00 $12.00 $4.50 76.2 1.78 — 6.7
GPT-5 (medium) OpenAI 22.9 — $1.25 $10.00 $3.44 0.0 0.00 — 6.7
Gemini 3.1 Pro Preview Google 29.7 68.8 $2.00 $12.00 $4.50 140.5 21.05 — 6.6
GPT-5.4 mini (Non-Reasoning) OpenAI 11.1 — $0.75 $4.50 $1.69 0.0 0.00 — 6.6
Qwen3 Max Alibaba 15.6 — $1.20 $6.00 $2.40 0.0 0.00 — 6.5
o3-mini OpenAI 12.5 — $1.10 $4.40 $1.93 0.0 0.00 — 6.5
Claude Opus 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback) Anthropic 51.2 — $4.00 $20.00 $8.00 75.7 8.87 — 6.4
GPT-5.2 (xhigh) OpenAI 30.4 — $1.75 $14.00 $4.81 0.0 0.00 — 6.3
Qwen3 14B (Reasoning) Alibaba 8.2 13.8 $0.35 $4.20 $1.31 0.0 0.00 — 6.2
Gemini 3 Pro Preview (high) Google 28.0 — $2.00 $12.00 $4.50 0.0 0.00 — 6.2
GPT-5.6 Terra (low) OpenAI 27.5 58.1 $2.00 $12.00 $4.50 73.5 1.75 — 6.1
Claude Sonnet 5 (Adaptive Reasoning, Low Effort) Anthropic 24.3 — $2.00 $10.00 $4.00 61.2 1.17 — 6.1
GPT-5 (low) OpenAI 20.8 — $1.25 $10.00 $3.44 0.0 0.00 — 6.1
GPT-5.2 Codex (xhigh) OpenAI 28.5 — $1.75 $14.00 $4.81 0.0 0.00 — 5.9
GPT-5.6 Sol (max) OpenAI 47.0 77.4 $4.00 $20.00 $8.00 62.1 64.25 — 5.9
Claude Sonnet 5 (Non-reasoning, High Effort) Anthropic 23.2 66.4 $2.00 $10.00 $4.00 59.2 1.09 — 5.8
o3 OpenAI 20.2 — $2.00 $8.00 $3.50 147.6 5.76 — 5.8
Llama 3.1 Nemotron Instruct 70B NVIDIA 6.9 — $1.20 $1.20 $1.20 44.5 5.97 — 5.8
Kimi K3 (low) Kimi 34.5 72.0 $3.00 $15.00 $6.00 36.4 2.99 — 5.8
o3-mini (high) OpenAI 11.0 16.3 $1.10 $4.40 $1.93 0.0 0.00 — 5.7
GPT-5.2 (medium) OpenAI 26.5 — $1.75 $14.00 $4.81 0.0 0.00 — 5.5
GPT-5.6 Sol (xhigh) OpenAI 44.0 78.3 $4.00 $20.00 $8.00 62.0 26.89 — 5.5
GPT-5.6 Sol (high) OpenAI 42.3 77.2 $4.00 $20.00 $8.00 63.4 9.05 — 5.3
Claude Opus 5.5 (Adaptive Reasoning, Low Effort, Default Fallback) Anthropic 42.3 — $4.00 $20.00 $8.00 70.5 2.82 — 5.3
Qwen3 Max (Preview) Alibaba 12.6 — $1.20 $6.00 $2.40 0.0 0.00 — 5.3
Claude Opus 5 (Adaptive Reasoning, Max Effort) Anthropic 50.8 78.0 $5.00 $25.00 $10.00 51.8 33.62 — 5.1
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) Anthropic 30.1 63.0 $3.00 $15.00 $6.00 0.0 0.00 — 5.0
Hermes 4 - Llama-3.1 405B (Reasoning) Nous Research 7.5 — $1.00 $3.00 $1.50 39.7 0.85 — 5.0
Nova Pro Amazon 7.0 — $0.80 $3.20 $1.40 0.0 0.00 — 5.0
Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) Anthropic 49.7 77.0 $5.00 $25.00 $10.00 55.2 24.22 — 5.0
Gemini 3 Pro Preview (low) Google 22.3 — $2.00 $12.00 $4.50 0.0 0.00 — 5.0
Hermes 4 - Llama-3.1 405B (Non-reasoning) Nous Research 7.4 — $1.00 $3.00 $1.50 39.8 0.90 — 4.9
GPT-5.4 (low) OpenAI 27.6 — $2.50 $15.00 $5.63 0.0 0.00 — 4.9
GPT-5.6 Sol (medium) OpenAI 39.2 76.3 $4.00 $20.00 $8.00 60.8 4.59 — 4.9
Grok 4.20 0309 (Non-reasoning) SpaceXAI 14.6 — $2.00 $6.00 $3.00 0.0 0.00 — 4.9
Claude Opus 5 (Adaptive Reasoning, High Effort) Anthropic 48.1 76.5 $5.00 $25.00 $10.00 54.3 9.67 — 4.8
Mistral Medium 3.5 Mistral 14.2 46.9 $1.50 $7.50 $3.00 162.2 0.60 — 4.7
Gemini 2.5 Pro Google 16.1 33.3 $1.25 $10.00 $3.44 0.0 0.00 — 4.7
Llama 3 Instruct 70B Meta 5.5 — $0.65 $2.75 $1.18 0.0 0.00 — 4.7
GPT-5.6 Terra (Non-reasoning) OpenAI 20.8 52.3 $2.00 $12.00 $4.50 72.7 0.92 — 4.6
DeepSeek R1 (Jan '25) DeepSeek 11.4 24.6 $2.00 $4.00 $2.50 0.0 0.00 — 4.6
Claude Opus 5 (Adaptive Reasoning, Medium Effort) Anthropic 44.8 74.3 $5.00 $25.00 $10.00 49.9 7.94 — 4.5
Gemini 2.5 Pro Preview (May' 25) Google 14.5 — $1.25 $10.00 $3.44 0.0 0.00 — 4.2
GPT-5.6 Sol (low) OpenAI 33.5 69.7 $4.00 $20.00 $8.00 61.5 2.62 — 4.2
Claude Opus 4.8 (Adaptive Reasoning, Max Effort) Anthropic 41.8 74.3 $5.00 $25.00 $10.00 0.0 0.00 — 4.2
Nova 2.0 Pro Preview (medium) Amazon 14.2 34.0 $1.25 $10.00 $3.44 118.6 15.76 — 4.1
Claude Sonnet 4.6 (Non-reasoning, High Effort) Anthropic 24.7 — $3.00 $15.00 $6.00 0.0 0.00 — 4.1
Claude Opus 4.7 (Adaptive Reasoning, Max Effort) Anthropic 40.7 73.6 $5.00 $25.00 $10.00 0.0 0.00 — 4.1
Qwen3 Coder 480B A35B Instruct Alibaba 11.9 — $1.50 $7.50 $3.00 0.0 0.00 — 4.0
Claude Opus 5 (Adaptive Reasoning, Low Effort) Anthropic 39.4 66.9 $5.00 $25.00 $10.00 55.6 2.67 — 3.9
Claude Sonnet 4.6 (Non-reasoning, Low Effort) Anthropic 23.3 — $3.00 $15.00 $6.00 0.0 0.00 — 3.9
GPT-5.1 (Non-reasoning) OpenAI 13.3 — $1.25 $10.00 $3.44 0.0 0.00 — 3.9
Apertus 70B Instruct Swiss AI Initiative 5.1 — $0.82 $2.92 $1.34 0.0 0.00 — 3.8
Grok 4 SpaceXAI 22.5 — $3.00 $15.00 $6.00 0.0 0.00 — 3.8
Nova 2.0 Pro Preview (low) Amazon 12.8 25.9 $1.25 $10.00 $3.44 127.1 5.21 — 3.7
GPT-4.1 OpenAI 12.7 — $2.00 $8.00 $3.50 0.0 0.00 — 3.6
Qwen3 235B A22B (Reasoning) Alibaba 9.5 — $0.70 $8.40 $2.63 0.0 0.00 — 3.6
GPT-5.6 Sol (Non-reasoning) OpenAI 28.3 65.1 $4.00 $20.00 $8.00 62.2 1.15 — 3.5
GPT-5.2 (Non-reasoning) OpenAI 17.0 — $1.75 $14.00 $4.81 0.0 0.00 — 3.5
Claude 4.5 Sonnet (Reasoning) Anthropic 20.7 52.1 $3.00 $15.00 $6.00 0.0 0.00 — 3.4
GPT-5.5 (xhigh) OpenAI 38.4 74.9 $5.00 $30.00 $11.25 0.0 0.00 — 3.4
GPT-5 (minimal) OpenAI 11.4 — $1.25 $10.00 $3.44 0.0 0.00 — 3.3
GPT-5.5 (high) OpenAI 37.0 71.6 $5.00 $30.00 $11.25 0.0 0.00 — 3.3
GPT-5.4 (Non-reasoning) OpenAI 18.2 — $2.50 $15.00 $5.63 0.0 0.00 — 3.2
Claude 4.5 Sonnet (Non-reasoning) Anthropic 19.3 — $3.00 $15.00 $6.00 0.0 0.00 — 3.2
Claude Opus 4.6 (Adaptive Reasoning, Max Effort) Anthropic 31.9 — $5.00 $25.00 $10.00 0.0 0.00 — 3.2
Claude Opus 4.7 (Non-reasoning, High Effort) Anthropic 30.9 — $5.00 $25.00 $10.00 0.0 0.00 — 3.1
GPT-5.5 (medium) OpenAI 33.8 71.5 $5.00 $30.00 $11.25 0.0 0.00 — 3.0
Claude Opus 4.5 (Reasoning) Anthropic 29.1 — $5.00 $25.00 $10.00 0.0 0.00 — 2.9
Nova 2.0 Pro Preview (Non-reasoning) Amazon 10.0 20.9 $1.25 $10.00 $3.44 129.2 0.68 — 2.9
GPT-5.5 (low) OpenAI 30.7 60.9 $5.00 $30.00 $11.25 0.0 0.00 — 2.7
Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) Anthropic 53.4 81.6 $10.00 $50.00 $20.00 63.6 122.47 — 2.7
Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback) Anthropic 53.2 80.7 $10.00 $50.00 $20.00 58.8 37.52 — 2.7
Claude Opus 4.6 (Non-reasoning, High Effort) Anthropic 26.4 — $5.00 $25.00 $10.00 0.0 0.00 — 2.6
GPT-6 Astra (max) OpenAI 52.7 76.9 $10.00 $50.00 $20.00 54.3 203.02 — 2.6
GPT-6 Astra (xhigh) OpenAI 52.4 75.9 $10.00 $50.00 $20.00 49.4 80.91 — 2.6
Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback) Anthropic 51.2 79.1 $10.00 $50.00 $20.00 48.4 6.55 — 2.6
Claude 3.7 Sonnet (Non-reasoning) Anthropic 15.3 — $3.00 $15.00 $6.00 0.0 0.00 — 2.6
GPT-6 Astra (high) OpenAI 50.9 77.1 $10.00 $50.00 $20.00 48.6 24.04 — 2.5
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) Anthropic 49.6 76.5 $10.00 $50.00 $20.00 0.0 0.00 — 2.5
GPT-6 Astra (medium) OpenAI 49.6 76.7 $10.00 $50.00 $20.00 46.6 4.22 — 2.5
Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback) Anthropic 48.9 77.1 $10.00 $50.00 $20.00 48.9 5.46 — 2.4
Claude Opus 4.5 (Non-reasoning) Anthropic 23.7 — $5.00 $25.00 $10.00 0.0 0.00 — 2.4
Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback) Anthropic 46.8 75.2 $10.00 $50.00 $20.00 48.7 4.44 — 2.3
GPT-5.5 Instant (June 2026) OpenAI 26.0 39.4 $5.00 $30.00 $11.25 124.2 0.89 — 2.3
GPT-6 Astra (low) OpenAI 45.8 75.7 $10.00 $50.00 $20.00 46.4 1.76 — 2.3
Mistral Large 2 (Jul '24) Mistral 6.8 — $2.00 $6.00 $3.00 0.0 0.00 — 2.3
GPT-5.5 (Non-reasoning) OpenAI 23.2 56.5 $5.00 $30.00 $11.25 0.0 0.00 — 2.1
GPT-5.5 Instant (May 2026) OpenAI 22.7 — $5.00 $30.00 $11.25 0.0 0.00 — 2.0
GPT-4o (Nov '24) OpenAI 8.4 — $2.50 $10.00 $4.38 0.0 0.00 — 1.9
Mistral Medium Mistral 5.5 — $1.50 $7.50 $3.00 0.0 0.00 — 1.8
GPT-4o (Aug '24) OpenAI 7.7 — $2.50 $10.00 $4.38 0.0 0.00 — 1.8
Jamba 1.5 Large AI21 Labs 6.0 — $2.00 $8.00 $3.50 0.0 0.00 — 1.7
Command A Cohere 7.0 — $2.50 $10.00 $4.38 60.0 0.35 — 1.6
Grok 3 SpaceXAI 12.1 — $4.00 $20.00 $8.00 0.0 0.00 — 1.5
Claude 3.5 Sonnet (Oct '24) Anthropic 7.9 30.2 $3.00 $15.00 $6.00 0.0 0.00 — 1.3
Claude 3.5 Sonnet (June '24) Anthropic 7.2 26.0 $3.00 $15.00 $6.00 0.0 0.00 — 1.2
GPT-4o (May '24) OpenAI 7.3 24.2 $5.00 $15.00 $7.50 0.0 0.00 — 1.0
Mistral Large (Feb '24) Mistral 5.8 — $4.00 $12.00 $6.00 0.0 0.00 — 1.0
Claude 4.1 Opus (Reasoning) Anthropic 22.8 — $15.00 $75.00 $30.00 0.0 0.00 — 0.8
Claude 4 Opus (Reasoning) Anthropic 20.6 — $15.00 $75.00 $30.00 0.0 0.00 — 0.7
o3-pro OpenAI 21.9 — $20.00 $80.00 $35.00 0.0 0.00 — 0.6
Claude 4.1 Opus (Non-reasoning) Anthropic 18.6 — $15.00 $75.00 $30.00 0.0 0.00 — 0.6
o1 OpenAI 15.2 39.7 $15.00 $60.00 $26.25 0.0 0.00 — 0.6
Claude 4 Opus (Non-reasoning) Anthropic 16.6 — $15.00 $75.00 $30.00 0.0 0.00 — 0.6
GPT-4 Turbo OpenAI 7.0 21.5 $10.00 $30.00 $15.00 0.0 0.00 — 0.5
o1-preview OpenAI 11.4 34.0 $16.50 $66.00 $28.88 0.0 0.00 — 0.4
Claude 3 Opus Anthropic 8.7 19.5 $15.00 $75.00 $30.00 0.0 0.00 — 0.3
GPT-4 OpenAI 6.7 13.1 $30.00 $60.00 $37.50 0.0 0.00 — 0.2
o1-pro OpenAI 12.4 — $150.00 $600.00 $262.50 0.0 0.00 — 0.0
Motif 3 Motif Technologies 33.6 63.5 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Motif 3 (Beta) Motif Technologies 32.3 62.0 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Muse Spark Meta 31.3 58.6 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
K2 Horizon 375B A23B Institute of Foundation Models 30.5 61.5 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
MiMo-V2-Pro Xiaomi 28.6 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Nex-N2-Pro (based on Qwen3.5-397B-A17B) Nex AGI 28.2 59.1 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
JT-4.1 Flash 236B A21B China Mobile 27.3 52.4 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
GLM-5-Turbo Z AI 26.6 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
K2 Horizon MoVA 36B A4B Institute of Foundation Models 25.3 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
MiMo-V2-Omni-0327 Xiaomi 25.1 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Solar Open2 250B Upstage 24.7 45.0 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
MiMo-V2-Omni Xiaomi 23.9 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
GLM 5V Turbo (Reasoning) Z AI 23.5 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
A.X-K2 SK Telecom 22.7 38.8 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
MiMo-V2-Flash (Feb 2026) Xiaomi 22.4 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
G9v3-39A5B AI9Stars 21.8 33.1 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Qwen3 Max Thinking Alibaba 21.3 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
K2 Horizon 7B Institute of Foundation Models 20.6 38.6 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Grok 4.1 Fast (Reasoning) SpaceXAI 20.4 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
K-EXAONE 2.0 0803 LG AI Research 19.7 40.6 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Gemma 4 31B (Reasoning) Google 19.0 43.4 $0.00 $0.00 $0.00 35.4 0.96 — 0.0
Claude 4 Sonnet (Reasoning) Anthropic 18.9 37.6 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
JT-35B-Flash China Mobile 18.7 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
KAT-Coder-Pro V1 KwaiKAT 18.6 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Claude 3.7 Sonnet (Reasoning) Anthropic 17.7 36.4 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Doubao Seed Code ByteDance Seed 16.9 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Claude 4 Sonnet (Non-reasoning) Anthropic 16.6 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
MiMo-V2-Flash (Non-reasoning) Xiaomi 16.0 49.8 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
K2 Horizon 3.7B Institute of Foundation Models 15.6 26.1 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Gemini 2.5 Flash Preview (Sep '25) (Reasoning) Google 15.5 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Ling 3.0 Tiny InclusionAI 15.3 26.5 $0.00 $0.00 $0.00 40.1 3.65 — 0.0
Gemini 2.5 Pro Preview (Mar' 25) Google 15.0 46.7 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
DeepSeek V3.2 Speciale DeepSeek 14.5 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
K-EXAONE (Reasoning) LG AI Research 14.4 32.1 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
ERNIE 5.0 Thinking Preview Baidu 14.3 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Grok Code Fast 1 SpaceXAI 14.1 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Apriel-v1.5-15B-Thinker ServiceNow 13.8 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Apriel-v1.6-15B-Thinker ServiceNow 13.4 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
EXAONE 4.5 33B LG AI Research 13.2 23.6 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Command A+ Cohere 13.1 27.8 $0.00 $0.00 $0.00 243.8 0.17 — 0.0
GLM-4.5 (Reasoning) Z AI 12.8 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
MiniCPM5-2B OpenBMB 12.5 14.5 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning) Google 12.4 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
JT-MINI China Mobile 12.2 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Magistral Medium 1.2 Mistral 11.8 21.3 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Sonar Reasoning Pro Perplexity 11.8 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
HyperNova 60B 2605 (high, based on gpt-oss-120b) Multiverse Computing 11.7 23.2 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Nemotron Cascade 2 30B A3B NVIDIA 11.7 25.3 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Gemini 2.5 Flash Preview (Reasoning) Google 11.7 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
K2 Think V2 Institute of Foundation Models 11.5 21.0 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
LongCat Flash Lite LongCat 11.5 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
HyperCLOVA X SEED Think (32B) Naver 11.4 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Grok 4.1 Fast (Non-reasoning) SpaceXAI 11.3 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
K-EXAONE (Non-reasoning) LG AI Research 11.2 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Mi:dm K 2.5 Pro Korea Telecom 11.0 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Ring-1T InclusionAI 10.9 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
G9v3-3B AI9Stars 10.8 9.9 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
INTELLECT-3 Prime Intellect 10.6 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
GPT-5 (ChatGPT) OpenAI 10.4 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Solar Open 100B (Reasoning) Upstage 10.4 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Grok 3 Reasoning Beta SpaceXAI 10.4 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
MiniMax M1 40k MiniMax 10.0 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
North Mini Code Cohere 9.9 36.5 $0.00 $0.00 $0.00 83.5 0.22 — 0.0
K2-V2 (high) Institute of Foundation Models 9.9 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
o1-mini OpenAI 9.8 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Ling 2.6 Flash InclusionAI 9.7 25.3 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Tri-21B-think Preview Trillion Labs 9.6 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
GPT-4.5 (Preview) OpenAI 9.6 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
DiffusionGemma 26B A4B Google 9.5 19.7 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Gemini 2.0 Flash Thinking Experimental (Jan '25) Google 9.4 24.1 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Motif-2-12.7B-Reasoning Motif Technologies 9.2 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Ling-1T InclusionAI 9.2 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Nova Premier Amazon 9.2 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Solar Pro 2 (Preview) (Reasoning) Upstage 9.1 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Magistral Medium 1 Mistral 9.1 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
K2-V2 (medium) Institute of Foundation Models 9.0 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Devstral Medium Mistral 9.0 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Tri-21B-Think Trillion Labs 9.0 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
GPT-4o (March 2025, chatgpt-4o-latest) OpenAI 9.0 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Gemini 2.0 Flash (Feb '25) Google 8.9 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Claude 3.5 Haiku Anthropic 8.9 15.9 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Llama 3.3 Nemotron Super 49B v1 (Reasoning) NVIDIA 8.9 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Qwen3 4B 2507 (Reasoning) Alibaba 8.8 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
MiniCPM5-1B (Reasoning) OpenBMB 8.8 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Gemini 2.0 Pro Experimental (Feb '25) Google 8.7 25.5 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Devstral Small (May '25) Mistral 8.7 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
MiniCPM5-1B (Non-reasoning) OpenBMB 8.7 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Sonar Reasoning Perplexity 8.7 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Gemini 2.5 Flash Preview (Non-reasoning) Google 8.7 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Devstral 2 Mistral 8.6 31.3 $0.00 $0.00 $0.00 145.1 0.73 — 0.0
Nanbeige4.1-3B Nanbeige 8.4 9.6 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
LFM2.5-2.6B Liquid AI 8.4 7.7 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
DeepSeek R1 Distill Qwen 32B DeepSeek 8.4 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Magistral Small 1 Mistral 8.2 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Gemini 2.0 Flash (experimental) Google 8.2 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
EXAONE 4.0 32B (Reasoning) LG AI Research 8.2 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
DeepSeek R1 0528 Qwen3 8B DeepSeek 8.1 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Qwen2.5 Max Alibaba 8.0 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Hermes 4 - Llama-3.1 70B (Reasoning) Nous Research 7.9 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Gemini 1.5 Pro (Sep '24) Google 7.9 23.6 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Solar Pro 2 (Preview) (Non-reasoning) Upstage 7.9 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
DeepSeek R1 Distill Qwen 14B DeepSeek 7.8 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Falcon-H1R-7B TII UAE 7.8 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Gemma 4 E2B (Reasoning) Google 7.8 7.2 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Sonar Perplexity 7.7 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Step3 VL 10B StepFun 7.7 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Sonar Pro Perplexity 7.6 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Devstral Small (Jul '25) Mistral 7.6 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
QwQ 32B-Preview Alibaba 7.6 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Mistral Large 2 (Nov '24) Mistral 7.6 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Devstral Small 2 Mistral 7.5 29.3 $0.00 $0.00 $0.00 145.9 0.67 — 0.0
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) NVIDIA 7.5 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Solar Pro 2 (Reasoning) Upstage 7.5 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Granite 4.1 30B IBM 7.4 10.4 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Gemini 2.0 Flash-Lite (Feb '25) Google 7.4 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
NVIDIA Nemotron 3 Nano 4B NVIDIA 7.4 8.0 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Gemini 2.0 Flash-Lite (Preview) Google 7.3 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
K2-V2 (low) Institute of Foundation Models 7.3 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning) NVIDIA 7.3 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Kimi Linear 48B A3B Instruct Kimi 7.3 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Llama 3.1 Instruct 405B Meta 7.3 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Llama 3.3 Nemotron Super 49B v1 (Non-reasoning) NVIDIA 7.3 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Qwen3 4B (Reasoning) Alibaba 7.2 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
LFM2.5-8B-A1B Liquid AI 7.2 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Llama 3.1 Tulu3 405B Allen Institute for AI 7.2 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
GPT-4o (ChatGPT) OpenAI 7.2 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Pixtral Large Mistral 7.1 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Olmo 3.1 32B Think Allen Institute for AI 7.1 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Grok 2 (Dec '24) SpaceXAI 7.1 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Gemini 1.5 Flash (Sep '24) Google 7.1 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Qwen3 VL 4B (Reasoning) Alibaba 7.0 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Solar Pro 2 (Non-reasoning) Upstage 7.0 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Qwen3.5 2B (Reasoning) Alibaba 6.9 2.9 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Grok Beta SpaceXAI 6.9 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Qwen2.5 Instruct 32B Alibaba 6.9 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Qwen3 4B 2507 Instruct Alibaba 6.7 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Qwen2.5 Coder Instruct 32B Alibaba 6.7 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Hermes 4 - Llama-3.1 70B (Non-reasoning) Nous Research 6.7 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
DeepSeek-V2.5 (Dec '24) DeepSeek 6.6 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Qwen3 4B (Non-reasoning) Alibaba 6.6 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Gemini 2.0 Flash Thinking Experimental (Dec '24) Google 6.6 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
DeepSeek-V2.5 DeepSeek 6.6 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Olmo 3.1 32B Instruct Allen Institute for AI 6.5 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Mistral Saba Mistral 6.5 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
DeepSeek R1 Distill Llama 8B DeepSeek 6.5 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Gemma 4 E2B (Non-reasoning) Google 6.5 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Olmo 3 32B Think Allen Institute for AI 6.5 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Gemini 1.5 Pro (May '24) Google 6.4 19.8 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
R1 1776 Perplexity 6.4 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Llama 3.2 Instruct 90B (Vision) Meta 6.4 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Grok-1 SpaceXAI 6.3 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Qwen2 Instruct 72B Alibaba 6.3 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Phi-4 Mini Instruct Microsoft 6.3 3.8 $0.00 $0.00 $0.00 45.2 0.35 — 0.0
EXAONE 4.0 32B (Non-reasoning) LG AI Research 6.3 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Qwen3.5 2B (Non-reasoning) Alibaba 6.2 2.4 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Gemini 1.5 Flash-8B Google 6.2 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Qwen3.5 0.8B (Reasoning) Alibaba 6.1 0.0 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
DeepHermes 3 - Mistral 24B Preview (Non-reasoning) Nous Research 6.1 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Jamba 1.7 Large AI21 Labs 6.1 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
DeepSeek-Coder-V2 DeepSeek 6.0 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
OLMo 2 32B Allen Institute for AI 6.0 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Jamba 1.6 Large AI21 Labs 6.0 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
LFM2 24B A2B Liquid AI 5.9 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Gemini 1.5 Flash (May '24) Google 5.9 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Claude 3 Sonnet Anthropic 5.9 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Granite 4.1 3B IBM 5.9 4.7 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Gemini 1.0 Ultra Google 5.8 17.6 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Phi-3 Mini Instruct 3.8B Microsoft 5.8 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Gemma 3n E4B Instruct Preview (May '25) Google 5.8 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Phi-4 Multimodal Instruct Microsoft 5.8 — $0.00 $0.00 $0.00 16.9 0.36 — 0.0
Qwen2.5 Coder Instruct 7B Alibaba 5.8 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Mixtral 8x22B Instruct Mistral 5.7 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Llama 3.2 Instruct 3B Meta 5.7 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
MiniCPM-V 4.6 1.3B OpenBMB 5.7 0.7 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Jamba Reasoning 3B AI21 Labs 5.7 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Qwen3 VL 4B Instruct Alibaba 5.7 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Qwen1.5 Chat 110B Alibaba 5.7 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Olmo 3 7B Think Allen Institute for AI 5.6 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Claude 2.1 Anthropic 5.6 14.0 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
OLMo 2 7B Allen Institute for AI 5.6 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Molmo 7B-D Allen Institute for AI 5.6 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Ling-mini-2.0 InclusionAI 5.5 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
DeepSeek R1 Distill Qwen 1.5B DeepSeek 5.5 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Claude 2.0 Anthropic 5.5 12.9 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
DeepSeek-V2-Chat DeepSeek 5.5 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Arctic Instruct Snowflake 5.4 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Qwen Chat 72B Alibaba 5.4 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
LFM 40B Liquid AI 5.4 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Qwen3.5 0.8B (Non-reasoning) Alibaba 5.4 1.2 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
PALM-2 Google 5.4 4.6 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Gemini 1.0 Pro Google 5.3 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
DeepSeek Coder V2 Lite Instruct DeepSeek 5.3 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Sarvam M (Reasoning) Sarvam 5.3 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
DeepSeek LLM 67B Chat (V1) DeepSeek 5.3 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Llama 2 Chat 70B Meta 5.3 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Llama 2 Chat 13B Meta 5.3 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Command-R+ (Apr '24) Cohere 5.3 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
OpenChat 3.5 (1210) OpenChat 5.3 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
DBRX Instruct Databricks 5.3 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Exaone 4.0 1.2B (Reasoning) LG AI Research 5.3 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Exaone 4.0 1.2B (Non-reasoning) LG AI Research 5.2 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
LFM2.5-1.2B-Thinking Liquid AI 5.2 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Jamba 1.7 Mini AI21 Labs 5.2 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
LFM2 2.6B Liquid AI 5.2 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
LFM2.5-1.2B-Instruct Liquid AI 5.2 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Granite 4.0 H 1B IBM 5.2 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Qwen3 1.7B (Reasoning) Alibaba 5.2 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Jamba 1.6 Mini AI21 Labs 5.2 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Gemma 3 270M Google 5.1 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Granite 4.0 Micro IBM 5.1 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning) Nous Research 5.1 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Claude Instant Anthropic 5.0 7.8 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Command-R (Mar '24) Cohere 5.0 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Llama 65B Meta 5.0 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Qwen Chat 14B Alibaba 5.0 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Granite 4.0 1B IBM 5.0 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Molmo2-8B Allen Institute for AI 5.0 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
LFM2 8B A1B Liquid AI 4.9 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Qwen3 1.7B (Non-reasoning) Alibaba 4.9 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Gemma 3 27B Instruct Google 4.9 10.1 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Gemma 3 1B Instruct Google 4.8 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Gemma 3 4B Instruct Google 4.8 2.7 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Gemma 3n E2B Instruct Google 4.8 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Gemma 3n E4B Instruct Google 4.8 3.2 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Granite 4.0 350M IBM 4.8 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Granite 4.0 H 350M IBM 4.8 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
LFM2 1.2B Liquid AI 4.8 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
LFM2.5-VL-1.6B Liquid AI 4.8 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Llama 3.2 Instruct 1B Meta 4.8 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Qwen3 0.6B (Non-reasoning) Alibaba 4.8 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Qwen3 0.6B (Reasoning) Alibaba 4.8 — $0.00 $0.00 $0.00 0.0 0.00 — 0.0
Tiny Aya Global Cohere 4.8 — $0.00 $0.00 $0.00 130.8 0.22 — 0.0
Gemma 3 12B Instruct Google 3.8 5.8 $0.00 $0.00 $0.00 0.0 0.00 — 0.0
K2 Horizon 0.9B Institute of Foundation Models 3.0 3.4 $0.00 $0.00 $0.00 0.0 0.00 — 0.0

最も高価なモデルが最善とは限らない

業界には、価格が高いほど品質が高いという根強い思い込みがあります。しかしデータは別の物語を語ります。上の表をバリュースコアで並べ替えると、上位にランクされるモデルの多くがフラッグシップモデルのほんの一部の価格でありながら、知能やコーディングのベンチマークで同等かそれ以上のスコアを出していることがわかります。

これは大規模になると重要です。アプリケーションが1日100万リクエストを処理する場合、$2/Mモデルと$0.20/Mモデルの差は丸め誤差ではなく、月に数千ドルの差になります。そして安価なモデルの方が実際に速い場合もあります。小型または最適化されたモデルはより高いスループットを達成することが多いからです。

大手プロバイダーのフラッグシップモデルは最難関のベンチマーク（先端数学、博士レベルの科学、複雑な多段階推論）ではリードしています。しかし、ほとんどの本番ワークロードは博士レベルの科学ではありません。分類、抽出、要約、コード生成、会話タスクです。これらには中位モデルは妥協ではなく、適切なツールです。

推論モデルはさらに別の次元を加えます。回答前に余分な計算で「思考」し、難しい問題での精度を向上させますが、レイテンシーとコストも増加します。多段階の論理的推論を必要としないユースケースでは、標準モデルが10分の1の時間で同じ答えを出します。

この表のバリュースコア（知能を混合価格で割った値）は、このトレードオフを一目で可視化するためにあります。プロジェクトに最適なモデルは、利用可能な中で最も賢いモデルではありません。必要な賢さを、それを提供する最低価格で実現するモデルです。

ヨーロッパのインフラストラクチャ上に構築し、データ主権を尊重するプロバイダーを見つけたい場合は、Voie.fiをご覧ください。コンピュート、ストレージ、決済、セキュリティ、AIなど1,400以上のヨーロッパ本社のデジタルインフラプロバイダーのオープンインデックスです。