Open-weight AI models: benchmarks and pricing
Weights are the model files needed to run it yourself, with suitable software and hardware. Compare models with downloadable weights. Open weights do not automatically mean an open-source license, unrestricted commercial use, or free hosting. API prices here describe the reported hosted service; check each model’s license before deployment.
Which should you choose?
No single benchmark covers every use case. Try your own prompts and compare accuracy, response time, input/output support, and the actual bill.
AI models
| Model | Intelligence score | Benchmark cost (USD) | Input price / 1M tokens (USD) | Output price / 1M tokens (USD) | Output speed |
|---|---|---|---|---|---|
| A.X-K2SK Telecom | 22.70 | - | - | - | - |
| Agnes 2.5 Pro AlphaSapiens AI | 26.80 | - | 0.45 | 0.90 | 178 tok/s |
| Apertus 70B InstructSwiss AI Initiative | 5.10 | - | 0.82 | 2.92 | - |
| Apertus 8B InstructSwiss AI Initiative | 4.80 | - | 0.10 | 0.20 | - |
| Apriel-v1.5-15B-ThinkerServiceNow | 13.80 | - | 0.00 | 0.00 | - |
| Apriel-v1.6-15B-ThinkerServiceNow | 13.40 | - | 0.00 | 0.00 | - |
| Arctic InstructSnowflake | 5.40 | - | - | - | - |
| Cogito v2.1 (Reasoning)Deep Cogito | - | - | 1.25 | 1.25 | - |
| Command ACohere | 7.00 | - | 2.50 | 10.00 | 67 tok/s |
| Command-R (Mar '24)Cohere | 5.00 | - | - | - | - |
| Command-R+ (Apr '24)Cohere | 5.30 | - | - | - | - |
| DBRX InstructDatabricks | 5.30 | - | - | - | - |
| DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)Nous Research | 5.10 | - | - | - | - |
| DeepHermes 3 - Mistral 24B Preview (Non-reasoning)Nous Research | 6.10 | - | - | - | - |
| DeepSeek Coder V2 Lite InstructDeepSeek | 5.30 | - | - | - | - |
| DeepSeek LLM 67B Chat (V1)DeepSeek | 5.30 | - | - | - | - |
| DeepSeek R1 (Jan '25)DeepSeek | 11.40 | $461 | 2.00 | 4.00 | - |
| DeepSeek R1 0528 (May '25)DeepSeek | 13.10 | - | 1.35 | 3.00 | - |
| DeepSeek R1 0528 Qwen3 8BDeepSeek | 8.10 | - | - | - | - |
| DeepSeek R1 Distill Llama 70BDeepSeek | 7.90 | - | 0.70 | 1.10 | 21 tok/s |
| DeepSeek R1 Distill Llama 8BDeepSeek | 6.50 | - | - | - | - |
| DeepSeek R1 Distill Qwen 1.5BDeepSeek | 5.50 | - | - | - | - |
| DeepSeek R1 Distill Qwen 14BDeepSeek | 7.80 | - | - | - | - |
| DeepSeek R1 Distill Qwen 32BDeepSeek | 8.40 | - | - | - | - |
| DeepSeek V3 (Dec '24)DeepSeek | 8.50 | $25.4 | 0.32 | 0.89 | - |
| DeepSeek V3 0324DeepSeek | 9.70 | $87.2 | 0.84 | 1.18 | - |
| DeepSeek V3.1 (Non-reasoning)DeepSeek | 13.70 | - | 0.57 | 1.68 | - |
| DeepSeek V3.1 (Reasoning)DeepSeek | 13.50 | - | 0.59 | 1.69 | - |
| DeepSeek V3.1 Terminus (Non-reasoning)DeepSeek | 13.90 | - | 0.27 | 1.00 | - |
| DeepSeek V3.1 Terminus (Reasoning)DeepSeek | 15.40 | - | 1.64 | 2.75 | - |
| DeepSeek V3.2 (Non-reasoning)DeepSeek | 16.00 | - | 0.28 | 0.42 | - |
| DeepSeek V3.2 (Reasoning)DeepSeek | 21.50 | - | 0.28 | 0.42 | - |
| DeepSeek V3.2 Exp (Non-reasoning)DeepSeek | 13.90 | - | 0.28 | 0.42 | - |
| DeepSeek V3.2 Exp (Reasoning)DeepSeek | 16.60 | - | 0.28 | 0.42 | - |
| DeepSeek V3.2 SpecialeDeepSeek | 14.50 | - | - | - | - |
| DeepSeek V4 Flash (Non-reasoning)DeepSeek | 18.90 | - | 0.09 | 0.20 | - |
| DeepSeek V4 Flash (Reasoning, High Effort)DeepSeek | 24.80 | $210 | 0.13 | 0.28 | - |
| DeepSeek V4 Flash (Reasoning, Max Effort)DeepSeek | 24.60 | $191 | 0.13 | 0.28 | - |
| DeepSeek V4 Flash 0731 (Reasoning, Max Effort)DeepSeek | 34.50 | $474 | 0.44 | 1.32 | 128 tok/s |
| DeepSeek V4 Pro (Non-reasoning)DeepSeek | 20.80 | - | 0.43 | 0.87 | 73 tok/s |
| DeepSeek V4 Pro (Reasoning, High Effort)DeepSeek | 30.10 | - | 0.43 | 0.87 | 70 tok/s |
| DeepSeek V4 Pro (Reasoning, Max Effort)DeepSeek | 30.90 | $277 | 0.43 | 0.87 | 77 tok/s |
| DeepSeek V4 Pro 0813 (Reasoning, Max Effort)DeepSeek | 36.30 | $1122 | 1.32 | 3.96 | 80 tok/s |
| DeepSeek-Coder-V2DeepSeek | 6.00 | - | - | - | - |
| DeepSeek-V2-ChatDeepSeek | 5.50 | - | - | - | - |
| DeepSeek-V2.5DeepSeek | 6.60 | - | - | - | - |
| DeepSeek-V2.5 (Dec '24)DeepSeek | 6.60 | - | - | - | - |
| Devstral Small (Jul '25)Mistral | 7.60 | - | - | - | - |
| Devstral Small (May '25)Mistral | 8.70 | - | - | - | - |
| DiffusionGemma 26B A4BGoogle | 9.50 | - | - | - | - |
| ERNIE 4.5 300B A47BBaidu | 7.50 | - | 0.28 | 1.10 | - |
| Exaone 4.0 1.2B (Non-reasoning)LG AI Research | 5.20 | - | - | - | - |
| Exaone 4.0 1.2B (Reasoning)LG AI Research | 5.30 | - | - | - | - |
| EXAONE 4.0 32B (Non-reasoning)LG AI Research | 6.30 | - | - | - | - |
| EXAONE 4.0 32B (Reasoning)LG AI Research | 8.20 | - | - | - | - |
| EXAONE 4.5 33BLG AI Research | 13.20 | - | - | - | - |
| EXAONE 4.5 33B (Non-reasoning)LG AI Research | - | - | - | - | - |
| Falcon-H1R-7BTII UAE | 7.80 | - | - | - | - |
| G9v3-39A5BAI9Stars | 21.80 | - | 0.00 | 0.00 | - |
| G9v3-3BAI9Stars | 10.80 | - | 0.00 | 0.00 | - |
| Gemma 3 1B InstructGoogle | 4.80 | - | 0.00 | 0.00 | - |
| Gemma 3 270MGoogle | 5.10 | - | - | - | - |
| Gemma 3 4B InstructGoogle | 4.80 | - | 0.00 | 0.00 | - |
| Gemma 3n E2B InstructGoogle | 4.80 | - | 0.00 | 0.00 | - |
| Gemma 3n E4B InstructGoogle | 4.80 | - | - | - | - |
| Gemma 3n E4B Instruct Preview (May '25)Google | 5.80 | - | - | - | - |
| Gemma 4 12B (Non-reasoning)Google | 9.40 | - | 0.10 | 0.30 | 107 tok/s |
| Gemma 4 12B (Reasoning)Google | 14.20 | - | 0.10 | 0.30 | 108 tok/s |
| Gemma 4 26B A4B (Non-reasoning)Google | 13.10 | - | 0.13 | 0.40 | 82 tok/s |
| Gemma 4 26B A4B (Reasoning)Google | 16.70 | - | 0.12 | 0.37 | - |
| Gemma 4 31B (Non-reasoning)Google | 13.90 | - | 0.14 | 0.40 | 60 tok/s |
| Gemma 4 E2B (Non-reasoning)Google | 6.50 | - | - | - | - |
| Gemma 4 E2B (Reasoning)Google | 7.80 | - | - | - | - |
| Gemma 4 E4B (Non-reasoning)Google | 7.50 | - | 0.02 | 0.10 | 40 tok/s |
| Gemma 4 E4B (Reasoning)Google | 8.90 | - | 0.02 | 0.10 | 41 tok/s |
| GLM-4.5 (Reasoning)Z AI | 12.80 | - | - | - | - |
| GLM-4.5-AirZ AI | 11.10 | - | 0.17 | 0.98 | 64 tok/s |
| GLM-4.5V (Non-reasoning)Z AI | 6.70 | - | 0.60 | 1.80 | 51 tok/s |
| GLM-4.5V (Reasoning)Z AI | 7.60 | - | 0.60 | 1.80 | 46 tok/s |
| GLM-4.6 (Non-reasoning)Z AI | 14.90 | - | 0.57 | 2.20 | 69 tok/s |
| GLM-4.6 (Reasoning)Z AI | 18.50 | - | 0.55 | 2.20 | 53 tok/s |
| GLM-4.6V (Non-reasoning)Z AI | 8.40 | - | 0.30 | 0.90 | 44 tok/s |
| GLM-4.6V (Reasoning)Z AI | 11.20 | - | 0.30 | 0.90 | 63 tok/s |
| GLM-4.7 (Non-reasoning)Z AI | 17.40 | - | 0.60 | 2.20 | 106 tok/s |
| GLM-4.7 (Reasoning)Z AI | 22.20 | - | 0.60 | 2.20 | 98 tok/s |
| GLM-4.7-Flash (Non-reasoning)Z AI | 10.60 | - | 0.07 | 0.40 | 94 tok/s |
| GLM-4.7-Flash (Reasoning)Z AI | 14.90 | - | 0.07 | 0.40 | 105 tok/s |
| GLM-5 (Non-reasoning)Z AI | 21.80 | - | 1.00 | 3.20 | 59 tok/s |
| GLM-5 (Reasoning)Z AI | 27.90 | - | 1.00 | 3.20 | 71 tok/s |
| GLM-5.1 (Non-reasoning)Z AI | 24.20 | - | 1.38 | 4.40 | 41 tok/s |
| GLM-5.1 (Reasoning)Z AI | 27.40 | - | 1.20 | 4.40 | 57 tok/s |
| GLM-5.2 (max)Z AI | 38.60 | - | 1.40 | 4.40 | 64 tok/s |
| GLM-5.2 (Non-reasoning)Z AI | 22.40 | - | 1.40 | 4.40 | 117 tok/s |
| GLM-5.3 (max)Z AI | 44.90 | $2503 | 1.40 | 4.40 | 70 tok/s |
| GLM-5.3-FlashZ AIBest value frontier | 41.90 | $280 | 0.15 | 0.50 | 66 tok/s |
| gpt-oss-120b (high)OpenAI | 12.30 | $122 | 0.15 | 0.59 | 215 tok/s |
| gpt-oss-120b (low)OpenAI | 10.20 | - | 0.15 | 0.54 | 247 tok/s |
| gpt-oss-20b (high)OpenAI | 9.00 | $29.4 | 0.06 | 0.19 | 198 tok/s |
| gpt-oss-20b (low)OpenAI | 10.00 | - | 0.07 | 0.20 | 249 tok/s |
| Granite 3.3 8B (Non-reasoning)IBM | 4.90 | - | 0.03 | 0.25 | 16 tok/s |
| Granite 4.0 1BIBM | 5.00 | - | - | - | - |
| Granite 4.0 350MIBM | 4.80 | - | - | - | - |
| Granite 4.0 H 1BIBM | 5.20 | - | - | - | - |
| Granite 4.0 H 350MIBM | 4.80 | - | - | - | - |
| Granite 4.0 H SmallIBM | 6.00 | - | 0.06 | 0.25 | 22 tok/s |
| Granite 4.0 MicroIBM | 5.10 | - | - | - | - |
| Granite 4.1 30BIBM | 7.40 | - | - | - | - |
| Granite 4.1 3BIBM | 5.90 | - | - | - | - |
| Granite 4.1 8BIBM | 6.60 | - | 0.05 | 0.10 | 70 tok/s |
| Granite 4.2 30BIBM | 14.80 | - | 0.16 | 0.65 | 76 tok/s |
| Granite 4.2 3BIBMBest value frontier | 9.10 | $14.9 | 0.03 | 0.12 | 216 tok/s |
| Granite 4.2 8BIBM | 12.40 | - | 0.06 | 0.25 | 120 tok/s |
| Grok 2 (Dec '24)SpaceXAI | 7.10 | - | - | - | - |
| Grok-1SpaceXAI | 6.30 | - | - | - | - |
| Hermes 3 - Llama-3.1 70BNous Research | 6.00 | - | 0.70 | 0.70 | 29 tok/s |
| Hermes 4 - Llama-3.1 405B (Non-reasoning)Nous Research | 7.40 | - | 1.00 | 3.00 | 43 tok/s |
| Hermes 4 - Llama-3.1 405B (Reasoning)Nous Research | 7.50 | - | 1.00 | 3.00 | 42 tok/s |
| Hermes 4 - Llama-3.1 70B (Non-reasoning)Nous Research | 6.70 | - | - | - | - |
| Hermes 4 - Llama-3.1 70B (Reasoning)Nous Research | 7.90 | - | - | - | - |
| Hy3Tencent | 25.80 | $149 | 0.14 | 0.55 | 94 tok/s |
| Hy3-preview (Non-reasoning)Tencent | 17.00 | - | 0.06 | 0.21 | - |
| Hy3-preview (Reasoning)Tencent | 22.70 | - | 0.06 | 0.21 | - |
| HyperCLOVA X SEED Think (32B)Naver | 11.40 | - | - | - | - |
| HyperNova 60B 2605 (high, based on gpt-oss-120b)Multiverse Computing | 11.70 | - | 0.04 | 0.14 | 353 tok/s |
| Inkling (xhigh)Thinking Machines | 25.50 | $1026 | 1.00 | 4.05 | 72 tok/s |
| Inkling SmallThinking Machines | 26.10 | $241 | 0.30 | 1.20 | 126 tok/s |
| INTELLECT-3Prime Intellect | 10.60 | - | - | - | - |
| Jamba 1.5 LargeAI21 Labs | 6.00 | - | 2.00 | 8.00 | - |
| Jamba 1.5 MiniAI21 Labs | 5.20 | - | 0.20 | 0.40 | - |
| Jamba 1.6 LargeAI21 Labs | 6.00 | - | - | - | - |
| Jamba 1.6 MiniAI21 Labs | 5.20 | - | - | - | - |
| Jamba 1.7 LargeAI21 Labs | 6.10 | - | - | - | - |
| Jamba 1.7 MiniAI21 Labs | 5.20 | - | - | - | - |
| Jamba Reasoning 3BAI21 Labs | 5.70 | - | - | - | - |
| K-EXAONE (Non-reasoning)LG AI Research | 11.20 | - | - | - | - |
| K-EXAONE (Reasoning)LG AI Research | 14.40 | - | - | - | - |
| K-EXAONE 2.0LG AI Research | 19.70 | - | - | - | - |
| K2 Horizon 375B A23BMBZUAI Institute of Foundation Models | 33.90 | - | - | - | - |
| K2 Think V2MBZUAI Institute of Foundation Models | 11.50 | - | - | - | - |
| K2-V2 (high)MBZUAI Institute of Foundation Models | 9.90 | - | - | - | - |
| K2-V2 (low)MBZUAI Institute of Foundation Models | 7.30 | - | - | - | - |
| K2-V2 (medium)MBZUAI Institute of Foundation Models | 9.00 | - | - | - | - |
| Kimi K2Kimi | 12.70 | - | 0.57 | 2.30 | 40 tok/s |
| Kimi K2 0905Kimi | 15.30 | - | 0.60 | 2.50 | 40 tok/s |
| Kimi K2 ThinkingKimi | 22.00 | - | 0.60 | 2.50 | 121 tok/s |
| Kimi K2.5 (Non-reasoning)Kimi | 19.40 | - | 0.60 | 3.00 | - |
| Kimi K2.5 (Reasoning)Kimi | 23.50 | - | 0.60 | 2.75 | - |
| Kimi K2.6Kimi | 31.30 | - | 0.95 | 4.00 | 56 tok/s |
| Kimi K2.6 (Non-reasoning)Kimi | 23.60 | - | 0.95 | 4.00 | 51 tok/s |
| Kimi K2.7 CodeKimi | 26.30 | $993 | 0.95 | 4.00 | 71 tok/s |
| Kimi K3 (low)Kimi | 34.50 | - | 3.00 | 15.00 | 38 tok/s |
| Kimi K3 (max)Kimi | 43.80 | $3658 | 3.00 | 15.00 | 42 tok/s |
| Kimi Linear 48B A3B InstructKimi | 7.30 | - | - | - | - |
| LFM2 1.2BLiquid AI | 4.80 | - | - | - | - |
| LFM2 2.6BLiquid AI | 5.20 | - | - | - | - |
| LFM2 24B A2BLiquid AI | 5.90 | - | - | - | - |
| LFM2 8B A1BLiquid AI | 4.90 | - | - | - | - |
| LFM2.5-1.2B-InstructLiquid AI | 5.20 | - | - | - | - |
| LFM2.5-1.2B-ThinkingLiquid AI | 5.20 | - | - | - | - |
| LFM2.5-2.6BLiquid AI | 8.40 | - | 0.00 | 0.00 | 200 tok/s |
| LFM2.5-8B-A1BLiquid AI | 7.20 | - | 0.00 | 0.00 | - |
| LFM2.5-VL-1.6BLiquid AI | 4.80 | - | 0.00 | 0.00 | - |
| Ling 2.6 FlashInclusionAI | 9.70 | - | - | - | - |
| Ling 3.0 FlashInclusionAI | 24.90 | - | 0.07 | 0.22 | 310 tok/s |
| Ling-1TInclusionAI | 9.20 | - | - | - | - |
| Ling-2.6-1TInclusionAI | 17.00 | - | 0.30 | 2.50 | - |
| Ling-flash-2.0InclusionAI | 7.80 | - | 0.14 | 0.57 | 7 tok/s |
| Ling-mini-2.0InclusionAI | 5.50 | - | - | - | - |
| Llama 2 Chat 13BMeta | 5.30 | - | - | - | - |
| Llama 2 Chat 70BMeta | 5.30 | - | - | - | - |
| Llama 2 Chat 7BMeta | 5.70 | - | 0.05 | 0.25 | - |
| Llama 3 Instruct 70BMeta | 5.50 | - | 0.65 | 2.75 | - |
| Llama 3 Instruct 8BMeta | 4.80 | - | 0.04 | 0.14 | - |
| Llama 3.1 Instruct 405BMeta | 7.30 | - | - | - | - |
| Llama 3.1 Instruct 70BMeta | 6.60 | - | 0.56 | 0.56 | 60 tok/s |
| Llama 3.1 Instruct 8BMeta | 6.90 | - | 0.02 | 0.05 | 141 tok/s |
| Llama 3.1 Nemotron Instruct 70BNVIDIA | 6.90 | - | 1.20 | 1.20 | 31 tok/s |
| Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)NVIDIA | 7.30 | - | - | - | - |
| Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)NVIDIA | 7.50 | - | - | - | - |
| Llama 3.1 Tulu3 405BAllen Institute for AI | 7.20 | - | - | - | - |
| Llama 3.2 Instruct 11B (Vision)Meta | 5.40 | - | 0.34 | 0.34 | 12 tok/s |
| Llama 3.2 Instruct 1BMeta | 4.80 | - | - | - | - |
| Llama 3.2 Instruct 3BMeta | 5.70 | - | - | - | - |
| Llama 3.2 Instruct 90B (Vision)Meta | 6.40 | - | - | - | - |
| Llama 3.3 Instruct 70BMeta | 7.70 | - | 0.66 | 0.72 | 88 tok/s |
| Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)NVIDIA | 7.30 | - | - | - | - |
| Llama 3.3 Nemotron Super 49B v1 (Reasoning)NVIDIA | 8.90 | - | - | - | - |
| Llama 4 MaverickMeta | 9.30 | $45.5 | 0.26 | 0.91 | 93 tok/s |
| Llama 4 ScoutMeta | 6.50 | $77.6 | 0.19 | 0.68 | 93 tok/s |
| Llama 65BMeta | 5.00 | - | - | - | - |
| Llama Nemotron Super 49B v1.5 (Non-reasoning)NVIDIA | 7.40 | - | 0.40 | 0.40 | 35 tok/s |
| Llama Nemotron Super 49B v1.5 (Reasoning)NVIDIA | 9.00 | - | 0.40 | 0.40 | 41 tok/s |
| LongCat 2.0LongCat | 19.70 | $545 | 0.75 | 2.95 | 50 tok/s |
| LongCat Flash LiteLongCat | 11.50 | - | - | - | - |
| Magistral Small 1Mistral | 8.20 | - | - | - | - |
| Magistral Small 1.2Mistral | 8.60 | - | 0.50 | 1.50 | - |
| MiMo-V2-Flash (Feb 2026)Xiaomi | 22.40 | - | - | - | - |
| MiMo-V2-Flash (Non-reasoning)Xiaomi | 16.00 | - | - | - | - |
| MiMo-V2-Flash (Reasoning)Xiaomi | 20.80 | - | 0.10 | 0.30 | - |
| MiMo-V2.5XiaomiBest value frontier | 22.30 | $42.6 | 0.14 | 0.28 | 65 tok/s |
| MiMo-V2.5-ProXiaomiBest value frontier | 26.40 | $138 | 0.43 | 0.87 | 36 tok/s |
| MiMo-V2.5-Pro (Non-reasoning)Xiaomi | 18.30 | - | 0.43 | 0.87 | 36 tok/s |
| MiniCPM-V 4.6 1.3BOpenBMB | 5.70 | - | - | - | - |
| MiniCPM5-1B (Non-reasoning)OpenBMB | 8.70 | - | - | - | - |
| MiniCPM5-1B (Reasoning)OpenBMB | 8.80 | - | - | - | - |
| MiniCPM5-2BOpenBMB | 14.30 | - | - | - | - |
| MiniMax M1 40kMiniMax | 10.00 | - | - | - | - |
| MiniMax M1 80kMiniMax | 11.70 | - | 0.55 | 2.20 | - |
| MiniMax-M2MiniMax | 18.60 | - | 0.30 | 1.20 | 94 tok/s |
| MiniMax-M2.1MiniMax | 20.90 | - | 0.30 | 1.20 | 91 tok/s |
| MiniMax-M2.5MiniMax | 22.80 | - | 0.30 | 1.20 | 96 tok/s |
| MiniMax-M2.7MiniMax | 23.20 | $236 | 0.30 | 1.20 | 73 tok/s |
| MiniMax-M3MiniMax | 29.60 | $538 | 0.30 | 1.20 | 156 tok/s |
| Ministral 3 14BMistral | 6.00 | $250 | 0.20 | 0.20 | 92 tok/s |
| Ministral 3 3BMistral | 4.80 | $61.3 | 0.10 | 0.10 | 186 tok/s |
| Ministral 3 8BMistral | 5.50 | $169 | 0.15 | 0.15 | 89 tok/s |
| Mistral 7B InstructMistral | 5.00 | - | 0.25 | 0.25 | 76 tok/s |
| Mistral Large 2 (Jul '24)Mistral | 6.80 | - | 2.00 | 6.00 | - |
| Mistral Large 2 (Nov '24)Mistral | 7.60 | - | - | - | - |
| Mistral Large 3Mistral | 9.70 | $130 | 0.50 | 1.50 | 79 tok/s |
| Mistral Medium 3.5Mistral | 14.90 | $1160 | 1.50 | 7.50 | 148 tok/s |
| Mistral Small (Sep '24)Mistral | 5.80 | - | 0.20 | 0.60 | 160 tok/s |
| Mistral Small 3Mistral | 6.70 | - | 0.10 | 0.30 | 158 tok/s |
| Mistral Small 3.1Mistral | 7.40 | $35.8 | 0.10 | 0.30 | 150 tok/s |
| Mistral Small 3.2Mistral | 7.00 | $163 | 0.10 | 0.30 | 157 tok/s |
| Mistral Small 4 (Non-reasoning)Mistral | 9.00 | - | 0.15 | 0.60 | 158 tok/s |
| Mistral Small 4 (Reasoning)Mistral | 11.50 | $78.7 | 0.15 | 0.60 | 168 tok/s |
| Mixtral 8x22B InstructMistral | 5.70 | - | - | - | - |
| Mixtral 8x7B InstructMistral | 5.10 | - | 0.45 | 0.70 | - |
| Molmo 7B-DAllen Institute for AI | 5.60 | - | - | - | - |
| Molmo2-8BAllen Institute for AI | 5.00 | - | - | - | - |
| Motif 3Motif Technologies | 33.60 | - | - | - | - |
| Muse Glimmer (high)Meta | 18.10 | $152 | 0.35 | 1.50 | 104 tok/s |
| Nanbeige4.1-3BNanbeige | 8.40 | - | - | - | - |
| Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIA | 10.30 | - | 0.09 | 0.36 | - |
| Nemotron 3 Super 120B A12B (Reasoning)NVIDIA | 13.60 | $859 | 0.19 | 0.65 | 99 tok/s |
| Nemotron 3 Ultra 550B A55B (Reasoning)NVIDIA | 23.40 | $801 | 0.60 | 2.60 | 168 tok/s |
| Nemotron 3.5 LightningNVIDIA | 13.60 | $105 | 0.06 | 0.20 | 289 tok/s |
| Nemotron Cascade 2 30B A3BNVIDIA | 11.70 | - | - | - | - |
| Nex-N2-ProNex AGI | 28.20 | - | 0.50 | 2.50 | 115 tok/s |
| North Mini CodeCohere | 12.80 | - | 0.00 | 0.00 | 45 tok/s |
| NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)NVIDIA | 6.80 | - | 0.05 | 0.20 | 227 tok/s |
| NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)NVIDIA | 8.90 | $63.7 | 0.05 | 0.20 | 205 tok/s |
| NVIDIA Nemotron 3 Nano 4BNVIDIA | 7.40 | - | - | - | - |
| NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)NVIDIA | 5.80 | - | 0.20 | 0.60 | 70 tok/s |
| NVIDIA Nemotron Nano 12B v2 VL (Reasoning)NVIDIA | 7.50 | - | 0.20 | 0.60 | 32 tok/s |
| NVIDIA Nemotron Nano 9B V2 (Non-reasoning)NVIDIA | 6.80 | - | 0.05 | 0.20 | 146 tok/s |
| NVIDIA Nemotron Nano 9B V2 (Reasoning)NVIDIA | 7.40 | - | 0.04 | 0.16 | 110 tok/s |
| OLMo 2 32BAllen Institute for AI | 6.00 | - | - | - | - |
| OLMo 2 7BAllen Institute for AI | 5.60 | - | - | - | - |
| Olmo 3 32B ThinkAllen Institute for AI | 6.50 | - | - | - | - |
| Olmo 3 7B InstructAllen Institute for AI | 5.20 | - | 0.10 | 0.20 | - |
| Olmo 3 7B ThinkAllen Institute for AI | 5.60 | - | - | - | - |
| Olmo 3.1 32B InstructAllen Institute for AI | 6.50 | - | - | - | - |
| Olmo 3.1 32B ThinkAllen Institute for AI | 7.10 | - | 0.00 | 0.00 | - |
| OpenChat 3.5 (1210)OpenChat | 5.30 | - | - | - | - |
| Phi-3 Mini Instruct 3.8BMicrosoft | 5.80 | - | - | - | - |
| Phi-4Microsoft | 5.90 | - | 0.13 | 0.50 | 41 tok/s |
| Phi-4 Mini InstructMicrosoft | 6.30 | - | 0.00 | 0.00 | 45 tok/s |
| Phi-4 Multimodal InstructMicrosoft | 5.80 | - | 0.00 | 0.00 | 17 tok/s |
| Pixtral LargeMistral | 7.10 | - | - | - | - |
| Qwen Chat 14BAlibaba | 5.00 | - | - | - | - |
| Qwen Chat 72BAlibaba | 5.40 | - | - | - | - |
| Qwen1.5 Chat 110BAlibaba | 5.70 | - | - | - | - |
| Qwen2 Instruct 72BAlibaba | 6.30 | - | - | - | - |
| Qwen2.5 Coder Instruct 32BAlibaba | 6.70 | - | - | - | - |
| Qwen2.5 Coder Instruct 7B Alibaba | 5.80 | - | - | - | - |
| Qwen2.5 Instruct 32BAlibaba | 6.90 | - | - | - | - |
| Qwen2.5 Instruct 72BAlibaba | 7.70 | - | 0.47 | 0.49 | - |
| Qwen3 0.6B (Non-reasoning)Alibaba | 4.80 | - | - | - | - |
| Qwen3 0.6B (Reasoning)Alibaba | 4.80 | - | - | - | - |
| Qwen3 1.7B (Non-reasoning)Alibaba | 4.90 | - | - | - | - |
| Qwen3 1.7B (Reasoning)Alibaba | 5.20 | - | - | - | - |
| Qwen3 14B (Non-reasoning)Alibaba | 6.70 | - | 0.35 | 1.40 | 60 tok/s |
| Qwen3 14B (Reasoning)Alibaba | 6.40 | - | 0.35 | 4.20 | 58 tok/s |
| Qwen3 235B A22B (Non-reasoning)Alibaba | 8.30 | - | 0.70 | 2.80 | 61 tok/s |
| Qwen3 235B A22B (Reasoning)Alibaba | 9.50 | - | 0.70 | 8.40 | 58 tok/s |
| Qwen3 235B A22B 2507 (Reasoning)Alibaba | 12.70 | $235 | 0.23 | 2.30 | 57 tok/s |
| Qwen3 235B A22B 2507 InstructAlibaba | 12.00 | - | 0.23 | 0.92 | 59 tok/s |
| Qwen3 30B A3B (Non-reasoning)Alibaba | 6.60 | - | 0.20 | 0.80 | 107 tok/s |
| Qwen3 30B A3B (Reasoning)Alibaba | 7.60 | - | 0.20 | 2.40 | 104 tok/s |
| Qwen3 30B A3B 2507 (Reasoning)Alibaba | 9.80 | $188 | 0.20 | 2.40 | 141 tok/s |
| Qwen3 30B A3B 2507 InstructAlibaba | 7.50 | - | 0.20 | 0.80 | 148 tok/s |
| Qwen3 32B (Non-reasoning)Alibaba | 7.30 | - | 0.16 | 0.64 | 105 tok/s |
| Qwen3 32B (Reasoning)Alibaba | 7.20 | - | 0.16 | 0.64 | 104 tok/s |
| Qwen3 4B (Non-reasoning)Alibaba | 6.60 | - | - | - | - |
| Qwen3 4B (Reasoning)Alibaba | 7.20 | - | - | - | - |
| Qwen3 4B 2507 (Reasoning)Alibaba | 8.80 | - | - | - | - |
| Qwen3 4B 2507 InstructAlibaba | 6.70 | - | - | - | - |
| Qwen3 8B (Non-reasoning)Alibaba | 6.00 | - | 0.18 | 0.70 | 39 tok/s |
| Qwen3 8B (Reasoning)Alibaba | 5.20 | - | 0.18 | 2.10 | 39 tok/s |
| Qwen3 Coder 30B A3B InstructAlibaba | 9.60 | - | 0.45 | 2.25 | 90 tok/s |
| Qwen3 Coder 480B A35B InstructAlibaba | 11.90 | - | 1.50 | 7.50 | 57 tok/s |
| Qwen3 Coder NextAlibaba | 10.10 | $476 | 0.35 | 1.20 | 117 tok/s |
| Qwen3 Next 80B A3B (Reasoning)Alibaba | 11.20 | - | 0.15 | 1.20 | 193 tok/s |
| Qwen3 Next 80B A3B InstructAlibaba | 9.60 | - | 0.15 | 1.20 | 178 tok/s |
| Qwen3 Omni 30B A3B (Reasoning)Alibaba | 7.80 | - | 0.25 | 0.97 | 100 tok/s |
| Qwen3 Omni 30B A3B InstructAlibaba | 6.00 | - | 0.25 | 0.97 | 95 tok/s |
| Qwen3 VL 235B A22B (Reasoning)Alibaba | 13.40 | - | 0.40 | 4.00 | 56 tok/s |
| Qwen3 VL 235B A22B InstructAlibaba | 9.90 | - | 0.40 | 1.60 | 51 tok/s |
| Qwen3 VL 30B A3B (Reasoning)Alibaba | 9.50 | - | 0.20 | 2.40 | 110 tok/s |
| Qwen3 VL 30B A3B InstructAlibaba | 7.90 | - | 0.20 | 0.80 | 110 tok/s |
| Qwen3 VL 32B (Reasoning)Alibaba | 11.90 | - | 0.16 | 0.64 | 90 tok/s |
| Qwen3 VL 32B InstructAlibaba | 8.40 | - | 0.16 | 0.64 | 68 tok/s |
| Qwen3 VL 4B (Reasoning)Alibaba | 7.00 | - | - | - | - |
| Qwen3 VL 4B InstructAlibaba | 5.70 | - | - | - | - |
| Qwen3 VL 8B (Reasoning)Alibaba | 8.20 | - | 0.18 | 2.10 | 113 tok/s |
| Qwen3 VL 8B InstructAlibaba | 7.30 | - | 0.18 | 0.70 | 119 tok/s |
| Qwen3.5 0.8B (Non-reasoning)Alibaba | 5.40 | - | - | - | - |
| Qwen3.5 0.8B (Reasoning)Alibaba | 6.10 | - | - | - | - |
| Qwen3.5 122B A10B (Non-reasoning)Alibaba | 17.70 | - | 0.40 | 3.20 | 144 tok/s |
| Qwen3.5 122B A10B (Reasoning)Alibaba | 16.20 | $661 | 0.40 | 3.20 | 129 tok/s |
| Qwen3.5 27B (Non-reasoning)Alibaba | 19.40 | - | 0.30 | 2.40 | 84 tok/s |
| Qwen3.5 27B (Reasoning)Alibaba | 22.90 | - | 0.30 | 2.40 | 77 tok/s |
| Qwen3.5 2B (Non-reasoning)Alibaba | 6.20 | - | - | - | - |
| Qwen3.5 2B (Reasoning)Alibaba | 6.90 | - | - | - | - |
| Qwen3.5 35B A3B (Non-reasoning)Alibaba | 15.10 | - | 0.25 | 2.00 | 164 tok/s |
| Qwen3.5 35B A3B (Reasoning)Alibaba | 19.30 | - | 0.25 | 2.00 | 146 tok/s |
| Qwen3.5 397B A17B (Non-reasoning)Alibaba | 21.40 | - | 0.60 | 3.60 | 83 tok/s |
| Qwen3.5 397B A17B (Reasoning)Alibaba | 19.10 | $941 | 0.60 | 3.60 | 86 tok/s |
| Qwen3.5 4B (Non-reasoning)Alibaba | 10.80 | - | 0.03 | 0.15 | 22 tok/s |
| Qwen3.5 4B (Reasoning)Alibaba | 13.10 | - | 0.03 | 0.15 | 27 tok/s |
| Qwen3.5 9B (Non-reasoning)Alibaba | 13.30 | - | 0.17 | 0.25 | 85 tok/s |
| Qwen3.5 9B (Reasoning)Alibaba | 13.70 | - | 0.14 | 0.20 | 83 tok/s |
| Qwen3.6 27B (Non-reasoning)Alibaba | 19.80 | - | 0.60 | 3.60 | 58 tok/s |
| Qwen3.6 27B (Reasoning)Alibaba | 21.90 | $1145 | 0.60 | 3.60 | 57 tok/s |
| Qwen3.6 35B A3B (Non-reasoning)Alibaba | 15.20 | - | 0.38 | 2.25 | 144 tok/s |
| Qwen3.6 35B A3B (Reasoning)Alibaba | 22.30 | - | 0.38 | 2.25 | 120 tok/s |
| Qwen3.8 2.4T A95BAlibaba | 40.00 | $2632 | 2.00 | 6.00 | 40 tok/s |
| Qwen3.8 27B (low)Alibaba | 29.20 | - | 0.50 | 3.00 | 54 tok/s |
| Qwen3.8 27B (medium)Alibaba | 30.70 | - | 0.50 | 3.00 | 54 tok/s |
| Qwen3.8 27B (Non-reasoning)Alibaba | 22.40 | - | 0.50 | 3.00 | 56 tok/s |
| Qwen3.8 27B (xhigh)Alibaba | 33.90 | $1170 | 0.50 | 3.00 | 47 tok/s |
| Qwen3.8-Flash-NextAlibaba | 42.20 | - | 0.15 | 0.47 | 72 tok/s |
| QwQ 32BAlibaba | 9.50 | - | 0.66 | 1.00 | - |
| QwQ 32B-PreviewAlibaba | 7.60 | - | - | - | - |
| R1 1776Perplexity | 6.40 | - | - | - | - |
| Reka Flash 3Reka AI | 5.60 | - | 0.20 | 0.80 | - |
| Ring-1TInclusionAI | 10.90 | - | - | - | - |
| Ring-2.6-1TInclusionAI | 17.30 | $576 | 0.30 | 2.50 | 121 tok/s |
| Ring-flash-2.0InclusionAI | 7.20 | - | 0.14 | 0.57 | - |
| Sarvam 105B (high)Sarvam | 8.80 | - | 0.04 | 0.17 | - |
| Sarvam 30B (high)Sarvam | 6.60 | - | 0.03 | 0.11 | - |
| Sarvam M (Reasoning)Sarvam | 5.30 | - | 0.00 | 0.00 | - |
| Seed-OSS-36B-InstructByteDance Seed | 12.10 | - | 0.21 | 0.57 | 30 tok/s |
| Solar MiniUpstage | 6.40 | - | 0.15 | 0.15 | - |
| Solar Open 100B (Reasoning)Upstage | 10.40 | - | - | - | - |
| Solar Open2 250BUpstage | 24.70 | - | - | - | - |
| Step 3.5 FlashStepFun | 16.60 | - | 0.10 | 0.30 | 226 tok/s |
| Step 3.7 FlashStepFun | 19.50 | - | 0.20 | 1.15 | 81 tok/s |
| Step3 VL 10BStepFun | 7.70 | - | - | - | - |
| Tiny Aya GlobalCohere | 4.80 | - | 0.00 | 0.00 | - |
| Tri-21B-ThinkTrillion Labs | 9.00 | - | - | - | - |
| Tri-21B-think PreviewTrillion Labs | 9.60 | - | - | - | - |
| Trinity Large ThinkingArcee AI | 10.90 | $518 | 0.25 | 0.90 | 320 tok/s |
Guides
How we compare models
Intelligence uses the Artificial Analysis Intelligence Index. Benchmark cost is the total USD cost of running that test, including reasoning tokens; it is not a per-token API price. Rankings use the same dataset and calculations in every language. General benchmark scores do not measure performance in a particular language or task.