Modèles d’IA les plus rapides : vitesse de sortie
Modèles classés par tokens de sortie par seconde. Cette vitesse diffère du délai avant la première réponse et du temps total, surtout pour les modèles de raisonnement. Les mesures manquantes sont exclues.
Lequel choisir ?
Aucun benchmark ne couvre tous les usages. Testez vos propres requêtes et comparez la précision, le temps de réponse, les entrées et sorties prises en charge et la facture réelle.
Modèles d’IA
| Modèle | Score d’intelligence | Coût du benchmark (USD) | Prix d’entrée / 1 million de tokens (USD) | Prix de sortie / 1 million de tokens (USD) | Vitesse de sortie |
|---|---|---|---|---|---|
| Mercury 2Inception | 25.30 | - | 0.25 | 0.75 | 747 jeton/s |
| Granite 4.0 H SmallIBM | 5.20 | - | 0.06 | 0.25 | 411 jeton/s |
| LFM2.5-VL-1.6BLiquid AI | 1.00 | - | 0.00 | 0.00 | 383 jeton/s |
| Step 3.7 FlashStepFun | 30.30 | - | 0.20 | 1.15 | 376 jeton/s |
| HyperNova 60B 2605Multiverse Computing | 17.80 | $35.0 | 0.04 | 0.14 | 335 jeton/s |
| LFM2.5-8B-A1BLiquid AI | 8.30 | - | 0.00 | 0.00 | 333 jeton/s |
| Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIA | 14.90 | - | 0.07 | 0.30 | 325 jeton/s |
| Granite 3.3 8B (Non-reasoning)IBM | 1.80 | - | 0.03 | 0.25 | 323 jeton/s |
| gpt-oss-120b (low)OpenAIMeilleur rapport qualité-prix | 14.90 | $24.2 | 0.15 | 0.60 | 315 jeton/s |
| Llama 3.1 Nemotron Instruct 70BNVIDIA | 7.60 | - | 1.20 | 1.20 | 300 jeton/s |
| Step 3.5 Flash 2603StepFun | 26.00 | - | 0.10 | 0.30 | 289 jeton/s |
| NVIDIA Nemotron Nano 12B v2 VL (Reasoning)NVIDIA | 9.00 | - | 0.20 | 0.60 | 282 jeton/s |
| Nova MicroAmazon | 4.70 | - | 0.04 | 0.14 | 279 jeton/s |
| Gemini 3.1 Flash-LiteGoogle | 25.00 | $93.7 | 0.25 | 1.50 | 275 jeton/s |
| Step 3.5 FlashStepFun | 25.50 | - | 0.10 | 0.30 | 269 jeton/s |
| gpt-oss-120b (high)OpenAI | 23.80 | $96.3 | 0.15 | 0.60 | 256 jeton/s |
| NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)NVIDIA | 4.60 | - | 0.20 | 0.60 | 250 jeton/s |
| Qwen3.5 Omni FlashAlibaba | 19.00 | - | 0.10 | 0.80 | 248 jeton/s |
| Gemini 2.5 Flash-Lite (Reasoning)Google | 11.40 | - | 0.10 | 0.40 | 236 jeton/s |
| Gemini 2.5 Flash (Reasoning)Google | 20.10 | - | 0.30 | 2.50 | 233 jeton/s |
| gpt-oss-20b (low)OpenAI | 14.30 | - | 0.06 | 0.20 | 225 jeton/s |
| o3-mini (high)OpenAI | 15.60 | - | 1.10 | 4.40 | 215 jeton/s |
| Gemini 2.5 Flash (Non-reasoning)Google | 14.10 | - | 0.30 | 2.50 | 214 jeton/s |
| GPT-5.6 Luna (max)OpenAI | 51.20 | $870 | 1.00 | 6.00 | 210 jeton/s |
| gpt-oss-20b (high)OpenAI | 14.90 | $29.9 | 0.05 | 0.20 | 205 jeton/s |
| GPT-5.1 Codex mini (high)OpenAI | 30.60 | - | 0.25 | 2.00 | 205 jeton/s |
| o3-miniOpenAI | 19.00 | - | 1.10 | 4.40 | 204 jeton/s |
| Qwen3.7 MaxAlibaba | 46.00 | $1559 | 2.50 | 7.50 | 204 jeton/s |
| Gemini 2.5 Flash-Lite (Non-reasoning)Google | 6.90 | - | 0.10 | 0.40 | 203 jeton/s |
| Nemotron 3 Ultra 550B A55B (Reasoning)NVIDIA | 37.80 | $435 | 0.68 | 2.67 | 190 jeton/s |
| GPT-5.1 Codex (high)OpenAI | 34.70 | - | 1.25 | 10.00 | 185 jeton/s |
| Jamba 1.6 MiniAI21 Labs | 2.60 | - | 0.20 | 0.40 | 184 jeton/s |
| Gemini 3 Flash Preview (Reasoning)Google | 37.80 | - | 0.50 | 3.00 | 181 jeton/s |
| Mistral Small 4 (Reasoning)Mistral | 19.60 | - | 0.15 | 0.60 | 180 jeton/s |
| Qwen3 Next 80B A3B InstructAlibaba | 13.70 | - | 0.50 | 2.00 | 180 jeton/s |
| GPT-4o (Nov '24)OpenAI | 11.20 | - | 2.50 | 10.00 | 178 jeton/s |
| GPT-5 Codex (high)OpenAI | 36.10 | - | 1.25 | 10.00 | 177 jeton/s |
| Qwen3 Next 80B A3B (Reasoning)Alibaba | 16.70 | $401 | 0.50 | 6.00 | 176 jeton/s |
| GPT-5.6 Luna (low)OpenAI | 33.30 | $68.8 | 1.00 | 6.00 | 174 jeton/s |
| GPT-5.6 Luna (Non-reasoning)OpenAI | 26.60 | $51.4 | 1.00 | 6.00 | 174 jeton/s |
| GPT-5.6 Luna (xhigh)OpenAI | 49.10 | $479 | 1.00 | 6.00 | 173 jeton/s |
| GPT-5.2 Codex (xhigh)OpenAI | 40.10 | - | 1.75 | 14.00 | 173 jeton/s |
| Nova LiteAmazon | 6.90 | - | 0.06 | 0.24 | 171 jeton/s |
| GPT-5.6 Luna (high)OpenAIMeilleur rapport qualité-prix | 46.10 | $275 | 1.00 | 6.00 | 170 jeton/s |
| GPT-5 nano (high)OpenAI | 19.90 | - | 0.05 | 0.40 | 170 jeton/s |
| GPT-5.4 mini (xhigh)OpenAI | 40.00 | $1095 | 0.75 | 4.50 | 169 jeton/s |
| Gemini 3 Flash Preview (Non-reasoning)Google | 27.40 | - | 0.50 | 3.00 | 169 jeton/s |
| Qwen3.6 35B A3B (Non-reasoning)Alibaba | 24.20 | $496 | 0.38 | 2.25 | 167 jeton/s |
| Ministral 3 3BMistral | 6.80 | $91.8 | 0.10 | 0.10 | 167 jeton/s |
| Sarvam 30B (high)Sarvam | 6.60 | - | 0.03 | 0.11 | 166 jeton/s |
| GPT-5.6 Luna (medium)OpenAI | 38.10 | $106 | 1.00 | 6.00 | 165 jeton/s |
| Ling 2.6 FlashInclusionAI | 14.10 | - | 0.10 | 0.30 | 164 jeton/s |
| GPT-5 nano (medium)OpenAI | 19.00 | - | 0.05 | 0.40 | 164 jeton/s |
| o4-mini (high)OpenAI | 25.60 | - | 1.10 | 4.40 | 163 jeton/s |
| GPT-5.4 nano (Non-Reasoning)OpenAI | 17.60 | - | 0.20 | 1.25 | 163 jeton/s |
| GPT-5.4 mini (Non-Reasoning)OpenAI | 16.60 | - | 0.75 | 4.50 | 163 jeton/s |
| GPT-5.4 mini (medium)OpenAI | 29.80 | - | 0.75 | 4.50 | 163 jeton/s |
| Qwen3.5 35B A3B (Non-reasoning)Alibaba | 23.40 | - | 0.25 | 2.00 | 161 jeton/s |
| GPT-5.4 nano (xhigh)OpenAI | 38.20 | - | 0.20 | 1.25 | 161 jeton/s |
| GPT-5 nano (minimal)OpenAI | 8.00 | - | 0.05 | 0.40 | 160 jeton/s |
| GPT-5 (ChatGPT)OpenAI | 15.30 | - | 1.25 | 10.00 | 160 jeton/s |
| GPT-5.4 nano (medium)OpenAI | 30.20 | - | 0.20 | 1.25 | 159 jeton/s |
| Trinity Large ThinkingArcee AI | 24.50 | - | 0.23 | 0.88 | 158 jeton/s |
| Gemini 3.5 Flash (high)Google | 50.20 | $1041 | 1.50 | 9.00 | 157 jeton/s |
| NVIDIA Nemotron 3 Super 120B A12B (Reasoning)NVIDIA | 25.40 | $254 | 0.25 | 0.78 | 156 jeton/s |
| Nova 2.0 Lite (high)Amazon | 18.20 | $635 | 0.30 | 2.50 | 156 jeton/s |
| GLM-5.2 (max)Z AI | 51.10 | $925 | 1.40 | 4.40 | 155 jeton/s |
| Gemini 3.5 Flash (medium)Google | 45.40 | - | 1.50 | 9.00 | 154 jeton/s |
| Nova 2.0 Lite (medium)Amazon | 19.00 | - | 0.30 | 2.50 | 153 jeton/s |
| Mistral Small 3.1Mistral | 14.70 | $29.9 | 0.10 | 0.30 | 152 jeton/s |
| Grok 4.20 0309 v2 (Reasoning)SpaceXAI | 37.00 | - | 2.00 | 6.00 | 151 jeton/s |
| Mistral Small 3Mistral | 6.90 | - | 0.10 | 0.30 | 151 jeton/s |
| GPT-5.4 (xhigh)OpenAI | 51.40 | $2132 | 2.50 | 15.00 | 151 jeton/s |
| Mistral Small 3.2Mistral | 10.60 | $128 | 0.10 | 0.30 | 149 jeton/s |
| NVIDIA Nemotron Nano 9B V2 (Non-reasoning)NVIDIA | 7.40 | - | 0.05 | 0.20 | 148 jeton/s |
| GPT-4.1 nanoOpenAI | 9.60 | $48.7 | 0.10 | 0.40 | 147 jeton/s |
| Nova 2.0 Lite (low)Amazon | 17.80 | - | 0.30 | 2.50 | 147 jeton/s |
| Mistral Small (Sep '24)Mistral | 4.70 | - | 0.20 | 0.60 | 147 jeton/s |
| Qwen3.5 122B A10B (Non-reasoning)Alibaba | 27.60 | $216 | 0.40 | 3.20 | 146 jeton/s |
| Qwen3 30B A3B 2507 (Reasoning)Alibaba | 14.40 | $152 | 0.20 | 2.40 | 146 jeton/s |
| Mistral Small 4 (Non-reasoning)Mistral | 12.40 | - | 0.15 | 0.60 | 146 jeton/s |
| Gemini 3.5 Flash (minimal)Google | 34.90 | - | 1.50 | 9.00 | 143 jeton/s |
| Qwen3 30B A3B 2507 InstructAlibaba | 9.10 | - | 0.20 | 0.80 | 143 jeton/s |
| Llama 3.1 Instruct 8BMeta | 7.60 | - | 0.10 | 0.10 | 142 jeton/s |
| Mistral Small (Feb '24)Mistral | 3.60 | - | 1.00 | 3.00 | 141 jeton/s |
| Nex-N2-ProNex AGI | 41.00 | - | 0.50 | 2.50 | 141 jeton/s |
| Nova 2.0 Lite (Non-reasoning)Amazon | 11.80 | - | 0.30 | 2.50 | 139 jeton/s |
| Grok 4.20 0309 v2 (Non-reasoning)SpaceXAI | 21.80 | - | 2.00 | 6.00 | 139 jeton/s |
| GPT-5.6 Terra (max)OpenAI | 55.00 | $1754 | 2.50 | 15.00 | 136 jeton/s |
| Qwen3.5 35B A3B (Reasoning)Alibaba | 29.30 | - | 0.25 | 2.00 | 136 jeton/s |
| Qwen3.6 35B A3B (Reasoning)Alibaba | 31.60 | $334 | 0.25 | 1.49 | 136 jeton/s |
| Qwen3.5 122B A10B (Reasoning)Alibaba | 32.30 | $447 | 0.40 | 3.20 | 133 jeton/s |
| Gemini 2.5 ProGoogle | 25.80 | $610 | 1.25 | 10.00 | 132 jeton/s |
| Nova 2.0 Pro Preview (low)Amazon | 19.60 | $244 | 1.25 | 10.00 | 125 jeton/s |
| Ring-2.6-1TInclusionAI | 30.60 | $460 | 0.30 | 2.50 | 124 jeton/s |
| Kimi K2 ThinkingKimi | 32.70 | - | 0.60 | 2.50 | 123 jeton/s |
| GPT-5.6 Terra (xhigh)OpenAI | 51.60 | $740 | 2.50 | 15.00 | 123 jeton/s |
| Nova 2.0 Pro Preview (medium)Amazon | 21.80 | $407 | 1.25 | 10.00 | 123 jeton/s |
| Grok 4.3 (high)SpaceXAI | 37.60 | $288 | 1.25 | 2.50 | 122 jeton/s |
| NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)NVIDIA | 14.20 | $38.9 | 0.05 | 0.20 | 121 jeton/s |
| GPT-5.6 Terra (Non-reasoning)OpenAI | 34.00 | - | 2.50 | 15.00 | 121 jeton/s |
| Muse Spark 1.1 (xhigh)MetaMeilleur rapport qualité-prix | 50.60 | $548 | 1.25 | 4.25 | 118 jeton/s |
| Hy3-preview (Reasoning)Tencent | 33.60 | - | 0.12 | 0.43 | 118 jeton/s |
| GPT-5.4 (Non-reasoning)OpenAI | 27.70 | - | 2.50 | 15.00 | 118 jeton/s |
| GPT-5.6 Terra (high)OpenAI | 49.00 | $496 | 2.50 | 15.00 | 116 jeton/s |
| Gemini 3.1 Pro PreviewGoogle | 46.50 | $815 | 2.00 | 12.00 | 116 jeton/s |
| GPT-5.4 (low)OpenAI | 39.10 | - | 2.50 | 15.00 | 116 jeton/s |
| GPT-5.6 Terra (medium)OpenAIMeilleur rapport qualité-prix | 45.60 | $240 | 2.50 | 15.00 | 116 jeton/s |
| GLM-4.7-Flash (Non-reasoning)Z AI | 15.50 | - | 0.07 | 0.40 | 115 jeton/s |
| Granite 4.1 8BIBM | 6.70 | - | 0.05 | 0.10 | 115 jeton/s |
| Hy3-preview (Non-reasoning)Tencent | 26.10 | - | 0.12 | 0.43 | 115 jeton/s |
| Qwen3 VL 8B (Reasoning)Alibaba | 10.60 | - | 0.18 | 2.10 | 114 jeton/s |
| NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)NVIDIA | 7.40 | - | 0.05 | 0.20 | 114 jeton/s |
| o3OpenAI | 30.40 | - | 2.00 | 8.00 | 113 jeton/s |
| Qwen3 VL 30B A3B (Reasoning)Alibaba | 13.30 | - | 0.20 | 2.40 | 113 jeton/s |
| Qwen3 VL 8B InstructAlibaba | 8.40 | - | 0.18 | 0.70 | 113 jeton/s |
| Qwen3 VL 30B A3B InstructAlibaba | 10.00 | - | 0.20 | 0.80 | 112 jeton/s |
| GPT-5.6 Terra (low)OpenAI | 40.50 | $161 | 2.50 | 15.00 | 112 jeton/s |
| Grok 4.3 (medium)SpaceXAI | 36.00 | - | 1.25 | 2.50 | 109 jeton/s |
| GLM-4.7 (Reasoning)Z AI | 33.70 | $603 | 0.60 | 2.20 | 109 jeton/s |
| DeepSeek V4 Flash (Non-reasoning)DeepSeek | 28.70 | - | 0.14 | 0.28 | 108 jeton/s |
| Gemma 4 12B (Non-reasoning)Google | 13.20 | - | 0.10 | 0.30 | 107 jeton/s |
| Nova 2.0 Pro Preview (Non-reasoning)Amazon | 14.40 | $206 | 1.25 | 10.00 | 107 jeton/s |
| o1OpenAI | 23.40 | - | 15.00 | 60.00 | 107 jeton/s |
| Gemma 4 12B (Reasoning)Google | 22.00 | - | 0.10 | 0.30 | 106 jeton/s |
| Qwen2.5 TurboAlibaba | 6.30 | - | 0.05 | 0.20 | 105 jeton/s |
| Qwen3 30B A3B (Non-reasoning)Alibaba | 6.80 | - | 0.20 | 0.80 | 105 jeton/s |
| Grok 4.3 (Non-reasoning)SpaceXAI | 24.80 | $201 | 1.25 | 2.50 | 104 jeton/s |
| Llama 4 MaverickMeta | 14.30 | $38.2 | 0.35 | 0.85 | 104 jeton/s |
| DeepSeek V4 Flash (Reasoning, Max Effort)DeepSeekMeilleur rapport qualité-prix | 40.30 | $74.3 | 0.14 | 0.28 | 104 jeton/s |
| Grok 4.5 (high)SpaceXAIMeilleur rapport qualité-prix | 53.80 | $602 | 2.00 | 6.00 | 103 jeton/s |
| Qwen3 30B A3B (Reasoning)Alibaba | 9.30 | - | 0.20 | 2.40 | 102 jeton/s |
| GLM-4.7 (Non-reasoning)Z AI | 26.60 | - | 0.60 | 2.20 | 101 jeton/s |
| Qwen3 Omni 30B A3B (Reasoning)Alibaba | 9.60 | - | 0.25 | 0.97 | 101 jeton/s |
| Grok 4.3 (low)SpaceXAI | 35.40 | - | 1.25 | 2.50 | 101 jeton/s |
| GPT-5.1 (high)OpenAI | 36.90 | - | 1.25 | 10.00 | 100 jeton/s |
| GPT-5 (high)OpenAI | 34.70 | $813 | 1.25 | 10.00 | 100 jeton/s |
| Qwen3 Coder NextAlibaba | 21.10 | $247 | 0.35 | 1.20 | 99 jeton/s |
| GPT-4.1OpenAI | 19.40 | - | 2.00 | 8.00 | 98 jeton/s |
| Mistral Medium 3.5Mistral | 29.90 | $1483 | 1.50 | 7.50 | 96 jeton/s |
| GPT-5 mini (minimal)OpenAI | 14.30 | - | 0.25 | 2.00 | 96 jeton/s |
| Qwen3 Omni 30B A3B InstructAlibaba | 5.10 | - | 0.25 | 0.97 | 95 jeton/s |
| GLM-5.2 (Non-reasoning)Z AI | 34.10 | - | 2.09 | 6.38 | 95 jeton/s |
| GPT-5 mini (medium)OpenAI | 30.90 | - | 0.25 | 2.00 | 95 jeton/s |
| Qwen3 32B (Non-reasoning)Alibaba | 8.60 | - | 0.70 | 2.80 | 95 jeton/s |
| Sarvam 105B (high)Sarvam | 11.90 | - | 0.04 | 0.17 | 93 jeton/s |
| Ministral 3 8BMistral | 9.00 | $113 | 0.15 | 0.15 | 92 jeton/s |
| Qwen3 Coder 30B A3B InstructAlibaba | 13.60 | - | 0.45 | 2.25 | 92 jeton/s |
| Qwen3 VL 32B (Reasoning)Alibaba | 17.90 | - | 0.70 | 8.40 | 90 jeton/s |
| Qwen3 32B (Reasoning)Alibaba | 11.50 | - | 0.70 | 8.40 | 90 jeton/s |
| GPT-5 mini (high)OpenAI | 25.30 | - | 0.25 | 2.00 | 90 jeton/s |
| Mistral 7B InstructMistral | 2.10 | - | 0.25 | 0.25 | 90 jeton/s |
| Claude 4.5 Haiku (Reasoning)Anthropic | 29.60 | $564 | 1.00 | 5.00 | 90 jeton/s |
| Llama 4 ScoutMetaMeilleur rapport qualité-prix | 10.00 | $11.5 | 0.17 | 0.63 | 89 jeton/s |
| GPT-5 (medium)OpenAI | 33.70 | - | 1.25 | 10.00 | 89 jeton/s |
| GPT-5.1 (Non-reasoning)OpenAI | 20.40 | - | 1.25 | 10.00 | 88 jeton/s |
| MiniMax-M2.5MiniMax | 33.70 | - | 0.30 | 1.20 | 88 jeton/s |
| Hermes 4 - Llama-3.1 70B (Reasoning)Nous Research | 10.00 | - | 0.13 | 0.40 | 88 jeton/s |
| GLM-4.7-Flash (Reasoning)Z AI | 22.90 | - | 0.07 | 0.40 | 87 jeton/s |
| Mistral Medium 3.1Mistral | 14.70 | $132 | 0.40 | 2.00 | 87 jeton/s |
| GPT-5.3 Codex (xhigh)OpenAI | 44.30 | - | 1.75 | 14.00 | 86 jeton/s |
| Llama 3.2 Instruct 1BMeta | 1.10 | - | 0.10 | 0.10 | 86 jeton/s |
| Llama 3.3 Instruct 70BMeta | 9.40 | $78.0 | 0.58 | 0.71 | 85 jeton/s |
| Claude 4.5 Haiku (Non-reasoning)Anthropic | 23.70 | - | 1.00 | 5.00 | 85 jeton/s |
| GPT-4o (Aug '24)OpenAI | 9.60 | - | 2.50 | 10.00 | 84 jeton/s |
| MiniMax-M3MiniMaxMeilleur rapport qualité-prix | 44.40 | $204 | 0.30 | 1.20 | 84 jeton/s |
| Ministral 3 14BMistral | 11.10 | $120 | 0.20 | 0.20 | 82 jeton/s |
| Qwen3.5 27B (Non-reasoning)Alibaba | 29.30 | - | 0.30 | 2.40 | 81 jeton/s |
| MiniMax-M2MiniMax | 28.30 | - | 0.30 | 1.20 | 81 jeton/s |
| Magistral Small 1.2Mistral | 11.30 | - | 0.50 | 1.50 | 81 jeton/s |
| MiniMax-M2.1MiniMax | 31.40 | - | 0.30 | 1.20 | 80 jeton/s |
| GPT-5 (low)OpenAI | 31.20 | - | 1.25 | 10.00 | 79 jeton/s |
| NVIDIA Nemotron Nano 9B V2 (Reasoning)NVIDIA | 8.80 | - | 0.04 | 0.16 | 79 jeton/s |
| GPT-4o (May '24)OpenAI | 8.60 | - | 5.00 | 15.00 | 79 jeton/s |
| Ling-flash-2.0InclusionAI | 9.70 | - | 0.14 | 0.57 | 78 jeton/s |
| Claude Sonnet 5 (Adaptive Reasoning, Max Effort)Anthropic | 53.40 | $4010 | 2.00 | 10.00 | 78 jeton/s |
| Grok Build 0.1 0616SpaceXAI | 39.80 | $375 | 1.00 | 2.00 | 77 jeton/s |
| Hermes 4 - Llama-3.1 70B (Non-reasoning)Nous Research | 6.90 | - | 0.13 | 0.40 | 77 jeton/s |
| GLM-4.5-AirZ AI | 16.50 | - | 0.17 | 0.98 | 76 jeton/s |
| Qwen3.5 27B (Reasoning)Alibaba | 33.80 | - | 0.30 | 2.40 | 76 jeton/s |
| GPT-4.1 miniOpenAI | 14.80 | $74.7 | 0.40 | 1.60 | 74 jeton/s |
| GPT-5 (minimal)OpenAI | 17.20 | - | 1.25 | 10.00 | 74 jeton/s |
| Inkling (xhigh)Thinking Machines | 40.70 | - | 1.87 | 4.68 | 73 jeton/s |
| Mistral MediumMistral | 3.60 | - | 2.75 | 8.10 | 72 jeton/s |
| GPT-5.5 (high)OpenAI | 53.10 | $1719 | 5.00 | 30.00 | 70 jeton/s |
| MiMo-V2.5XiaomiMeilleur rapport qualité-prix | 37.20 | $25.2 | 0.14 | 0.28 | 69 jeton/s |
| Grok 3 mini Reasoning (high)SpaceXAI | 22.50 | - | 0.30 | 0.50 | 68 jeton/s |
| Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort)Anthropic | - | - | 2.00 | 10.00 | 68 jeton/s |
| Llama 3.1 Instruct 405BMeta | 8.50 | - | 2.75 | 6.50 | 68 jeton/s |
| GPT-5.2 (xhigh)OpenAI | 42.20 | - | 1.75 | 14.00 | 67 jeton/s |
| GPT-5.5 (xhigh)OpenAI | 54.80 | $2778 | 5.00 | 30.00 | 67 jeton/s |
| Qwen3 VL 32B InstructAlibaba | 11.10 | - | 0.70 | 2.80 | 66 jeton/s |
| Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)AnthropicMeilleur rapport qualité-prix | 59.90 | $5631 | 10.00 | 50.00 | 66 jeton/s |
| GPT-5.2 (Non-reasoning)OpenAI | 26.00 | - | 1.75 | 14.00 | 64 jeton/s |
| Claude Sonnet 5 (Adaptive Reasoning, High Effort)Anthropic | - | - | 2.00 | 10.00 | 64 jeton/s |
| Qwen3 14B (Non-reasoning)Alibaba | 7.00 | - | 0.35 | 1.40 | 64 jeton/s |
| GPT-5.5 (medium)OpenAI | 50.40 | $936 | 5.00 | 30.00 | 64 jeton/s |
| Claude Sonnet 5 (Non-reasoning, High Effort)Anthropic | 41.70 | $427 | 2.00 | 10.00 | 63 jeton/s |
| DeepSeek V4 Pro (Reasoning, Max Effort)DeepSeekMeilleur rapport qualité-prix | 44.30 | $176 | 0.43 | 0.87 | 62 jeton/s |
| GPT-5.5 (low)OpenAI | 43.50 | $375 | 5.00 | 30.00 | 62 jeton/s |
| GLM-4.6V (Non-reasoning)Z AI | 11.00 | - | 0.30 | 0.90 | 62 jeton/s |
| Kimi K3Kimi | 57.10 | $2691 | 3.00 | 15.00 | 62 jeton/s |
| GLM-5.1 (Reasoning)Z AI | 40.20 | $659 | 1.40 | 4.40 | 62 jeton/s |
| GPT-5.5 (Non-reasoning)OpenAI | 35.40 | $211 | 5.00 | 30.00 | 61 jeton/s |
| Claude Sonnet 5 (Adaptive Reasoning, Medium Effort)Anthropic | - | - | 2.00 | 10.00 | 61 jeton/s |
| DeepSeek V4 Pro (Reasoning, High Effort)DeepSeek | 40.80 | - | 0.43 | 0.87 | 61 jeton/s |
| MiniMax-M2.7MiniMax | 38.10 | - | 0.30 | 1.20 | 60 jeton/s |
| Claude Sonnet 5 (Adaptive Reasoning, Low Effort)Anthropic | - | - | 2.00 | 10.00 | 60 jeton/s |
| Qwen3.5 397B A17B (Reasoning)Alibaba | 33.70 | $528 | 0.60 | 3.60 | 60 jeton/s |
| Qwen3 235B A22B (Reasoning)Alibaba | 13.40 | - | 0.70 | 8.40 | 59 jeton/s |
| Qwen3 14B (Reasoning)Alibaba | 10.40 | - | 0.35 | 4.20 | 59 jeton/s |
| Qwen3.5 9B (Reasoning)Alibaba | 21.40 | $179 | 0.10 | 0.15 | 59 jeton/s |
| MiMo-V2.5-Pro (Non-reasoning)Xiaomi | 27.90 | - | 0.66 | 1.72 | 58 jeton/s |
| GPT-4o miniOpenAI | 6.90 | - | 0.15 | 0.60 | 58 jeton/s |
| Qwen3 235B A22B 2507 InstructAlibaba | 18.20 | - | 0.70 | 2.80 | 58 jeton/s |
| DeepSeek V4 Pro (Non-reasoning)DeepSeek | 31.20 | - | 0.43 | 0.87 | 58 jeton/s |
| Qwen3.5 397B A17B (Non-reasoning)Alibaba | 32.00 | - | 0.60 | 3.60 | 57 jeton/s |
| MiMo-V2.5-ProXiaomiMeilleur rapport qualité-prix | 42.20 | $98.5 | 0.43 | 0.87 | 57 jeton/s |
| Llama 3.2 Instruct 90B (Vision)Meta | 6.20 | - | 1.38 | 1.38 | 57 jeton/s |
| Qwen3 MaxAlibaba | 24.00 | - | 1.20 | 6.00 | 57 jeton/s |
| GLM-4.5V (Non-reasoning)Z AI | 7.00 | - | 0.60 | 1.80 | 57 jeton/s |
| Reka Flash (Sep '24)Reka AI | 6.30 | - | 0.20 | 0.80 | 57 jeton/s |
| Qwen3 235B A22B (Non-reasoning)Alibaba | 10.90 | - | 0.70 | 2.80 | 57 jeton/s |
| Claude Opus 4.8 (Adaptive Reasoning, Max Effort)Anthropic | 55.70 | $3753 | 5.00 | 25.00 | 56 jeton/s |
| Qwen3 Max (Preview)Alibaba | 19.20 | - | 1.20 | 6.00 | 56 jeton/s |
| Jamba 1.6 LargeAI21 Labs | 5.00 | - | 2.00 | 8.00 | 56 jeton/s |
| Qwen3.6 27B (Non-reasoning)Alibaba | 30.50 | $356 | 0.60 | 3.60 | 56 jeton/s |
| Gemma 4 26B A4B (Non-reasoning)Google | 20.10 | - | 0.13 | 0.40 | 55 jeton/s |
| Qwen3 235B A22B 2507 (Reasoning)Alibaba | 19.60 | - | 0.70 | 8.40 | 55 jeton/s |
| Qwen3.5 Omni PlusAlibaba | 30.60 | - | 0.40 | 4.80 | 55 jeton/s |
| Jamba 1.7 LargeAI21 Labs | 5.30 | - | 2.00 | 8.00 | 55 jeton/s |
| Qwen3 VL 235B A22B (Reasoning)Alibaba | 20.60 | - | 0.70 | 8.40 | 54 jeton/s |
| Qwen3.6 27B (Reasoning)Alibaba | 37.10 | $668 | 0.60 | 3.60 | 54 jeton/s |
| Qwen3.6 PlusAlibaba | 39.60 | $526 | 0.50 | 3.00 | 53 jeton/s |
| Command ACohere | 7.70 | - | 2.50 | 10.00 | 53 jeton/s |
| Qwen3.7 PlusAlibaba | 39.00 | $303 | 0.40 | 1.60 | 53 jeton/s |
| GPT-5.6 Sol (max)OpenAIMeilleur rapport qualité-prix | 58.90 | $2824 | 5.00 | 30.00 | 53 jeton/s |
| Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)NVIDIA | 9.10 | - | 0.60 | 1.80 | 52 jeton/s |
| GPT-5.6 Sol (xhigh)OpenAIMeilleur rapport qualité-prix | 57.70 | $1543 | 5.00 | 30.00 | 52 jeton/s |
| Llama 3.2 Instruct 3BMeta | 4.20 | - | 0.15 | 0.15 | 52 jeton/s |
| Mistral Large 3Mistral | 15.90 | $71.0 | 0.50 | 1.50 | 52 jeton/s |
| GLM-5.1 (Non-reasoning)Z AI | 35.40 | - | 1.40 | 4.40 | 52 jeton/s |
| GPT-5.6 Sol (medium)OpenAIMeilleur rapport qualité-prix | 53.60 | $593 | 5.00 | 30.00 | 52 jeton/s |
| Qwen3 VL 235B A22B InstructAlibaba | 14.30 | - | 0.70 | 2.80 | 51 jeton/s |
| Kimi K2.5 (Reasoning)Kimi | 35.40 | - | 0.60 | 3.00 | 51 jeton/s |
| GLM-5 (Non-reasoning)Z AI | 32.40 | - | 1.00 | 3.20 | 51 jeton/s |
| Qwen3 Max Thinking (Preview)Alibaba | 25.00 | - | 1.20 | 6.00 | 51 jeton/s |
| GPT-5.6 Sol (low)OpenAIMeilleur rapport qualité-prix | 49.40 | $353 | 5.00 | 30.00 | 50 jeton/s |
| Llama Nemotron Super 49B v1.5 (Non-reasoning)NVIDIA | 8.70 | - | 0.40 | 0.40 | 50 jeton/s |
| GPT-5.6 Sol (Non-reasoning)OpenAI | 41.20 | $242 | 5.00 | 30.00 | 50 jeton/s |
| Qwen3 Coder 480B A35B InstructAlibaba | 18.00 | - | 1.50 | 7.50 | 50 jeton/s |
| Claude Opus 4.7 (Adaptive Reasoning, Max Effort)Anthropic | 53.50 | $3738 | 5.00 | 25.00 | 50 jeton/s |
| Llama Nemotron Super 49B v1.5 (Reasoning)NVIDIA | 12.40 | - | 0.40 | 0.40 | 50 jeton/s |
| GLM-4.6 (Non-reasoning)Z AI | 23.00 | - | 0.57 | 2.20 | 49 jeton/s |
| Kimi K2.5 (Non-reasoning)Kimi | 29.40 | - | 0.60 | 3.00 | 48 jeton/s |
| Gemma 3n E4B InstructGoogle | 1.20 | - | 0.02 | 0.04 | 48 jeton/s |
| GLM-5 (Reasoning)Z AI | 39.50 | - | 1.00 | 3.20 | 48 jeton/s |
| GPT-5.6 Sol (high)OpenAIMeilleur rapport qualité-prix | 55.90 | $956 | 5.00 | 30.00 | 47 jeton/s |
| Kimi K2.6Kimi | 44.20 | - | 0.95 | 4.00 | 47 jeton/s |
| Llama 3.2 Instruct 11B (Vision)Meta | 3.30 | - | 0.34 | 0.34 | 47 jeton/s |
| Kimi K2.7 CodeKimi | 41.90 | - | 0.95 | 4.00 | 46 jeton/s |
| Kimi K2.6 (Non-reasoning)Kimi | 34.60 | - | 0.95 | 4.00 | 46 jeton/s |
| Claude Opus 4.7 (Non-reasoning, High Effort)Anthropic | 42.70 | - | 5.00 | 25.00 | 45 jeton/s |
| Claude Opus 4.5 (Reasoning)Anthropic | 40.80 | - | 5.00 | 25.00 | 45 jeton/s |
| Hy3Tencent | 41.20 | - | 0.00 | 0.00 | 45 jeton/s |
| Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)Anthropic | 47.20 | $3356 | 3.00 | 15.00 | 45 jeton/s |
| Mistral Medium 3Mistral | 12.50 | - | 0.40 | 2.00 | 43 jeton/s |
| Claude Opus 4.5 (Non-reasoning)Anthropic | 34.70 | - | 5.00 | 25.00 | 43 jeton/s |
| Magistral Medium 1.2Mistral | 17.90 | $886 | 2.00 | 5.00 | 43 jeton/s |
| Claude Sonnet 4.6 (Non-reasoning, High Effort)Anthropic | 35.90 | - | 3.00 | 15.00 | 43 jeton/s |
| GLM-4.5V (Reasoning)Z AI | 9.10 | - | 0.60 | 1.80 | 42 jeton/s |
| Claude Sonnet 4.6 (Non-reasoning, Low Effort)Anthropic | 34.30 | - | 3.00 | 15.00 | 42 jeton/s |
| Qwen3.6 Max PreviewAlibaba | 40.00 | - | 1.30 | 7.80 | 42 jeton/s |
| Claude 4.5 Sonnet (Reasoning)Anthropic | 36.40 | $1133 | 3.00 | 15.00 | 40 jeton/s |
| Claude 4.5 Sonnet (Non-reasoning)Anthropic | 29.30 | - | 3.00 | 15.00 | 40 jeton/s |
| GLM-4.6 (Reasoning)Z AI | 28.70 | $313 | 0.55 | 2.20 | 40 jeton/s |
| o3-proOpenAI | 32.50 | - | 20.00 | 80.00 | 39 jeton/s |
| Claude Opus 4.6 (Adaptive Reasoning, Max Effort)Anthropic | 43.70 | - | 5.00 | 25.00 | 39 jeton/s |
| Qwen3 8B (Reasoning)Alibaba | 8.30 | - | 0.18 | 2.10 | 38 jeton/s |
| Qwen3 8B (Non-reasoning)Alibaba | 5.10 | - | 0.18 | 0.70 | 38 jeton/s |
| Claude Opus 4.6 (Non-reasoning, High Effort)Anthropic | 37.80 | - | 5.00 | 25.00 | 38 jeton/s |
| Gemma 4 31B (Non-reasoning)Google | 21.80 | $29.0 | 0.14 | 0.40 | 37 jeton/s |
| Kimi K2 0905Kimi | 23.50 | - | 0.60 | 2.50 | 36 jeton/s |
| Hermes 3 - Llama-3.1 70BNous Research | 5.10 | - | 0.70 | 0.70 | 36 jeton/s |
| Gemma 4 31B (Reasoning)Google | 29.40 | - | 0.00 | 0.00 | 36 jeton/s |
| Kimi K2Kimi | 19.40 | - | 0.58 | 2.40 | 36 jeton/s |
| GLM-4.6V (Reasoning)Z AI | 16.80 | - | 0.30 | 0.90 | 35 jeton/s |
| Hermes 4 - Llama-3.1 405B (Non-reasoning)Nous Research | 8.80 | - | 1.00 | 3.00 | 34 jeton/s |
| Hermes 4 - Llama-3.1 405B (Reasoning)Nous Research | 9.00 | - | 1.00 | 3.00 | 34 jeton/s |
| Seed-OSS-36B-InstructByteDance Seed | 18.30 | - | 0.21 | 0.57 | 34 jeton/s |
| Nova PremierAmazon | 12.70 | - | 2.50 | 12.50 | 33 jeton/s |
| Llama 3.1 Instruct 70BMeta | 6.80 | - | 0.56 | 0.56 | 32 jeton/s |
| GPT-4 TurboOpenAI | 7.90 | - | 10.00 | 30.00 | 31 jeton/s |
| Phi-4Microsoft | 4.90 | - | 0.13 | 0.50 | 31 jeton/s |
| QwQ 32BAlibaba | 13.40 | - | 0.66 | 1.00 | 30 jeton/s |
| Claude 4.1 Opus (Reasoning)Anthropic | 33.70 | - | 15.00 | 75.00 | 30 jeton/s |
| Claude 4.1 Opus (Non-reasoning)Anthropic | 28.20 | - | 15.00 | 75.00 | 28 jeton/s |
| Qwen3.5 4B (Non-reasoning)Alibaba | 16.00 | - | 0.03 | 0.15 | 24 jeton/s |
| Qwen3.5 4B (Reasoning)Alibaba | 20.10 | - | 0.03 | 0.15 | 23 jeton/s |
| DeepSeek R1 Distill Llama 70BDeepSeek | 9.90 | - | 0.70 | 1.05 | 23 jeton/s |
| Phi-4 Multimodal InstructMicrosoft | 4.50 | - | 0.00 | 0.00 | 17 jeton/s |
Guides
Comment nous comparons les modèles
L’intelligence est mesurée par l’Artificial Analysis Intelligence Index. Le coût du benchmark correspond au coût total du test en USD, tokens de raisonnement compris ; ce n’est pas le tarif API par token. Toutes les langues utilisent les mêmes données et calculs. Le score général ne mesure pas les performances dans une langue ou une tâche précise.