Agentic leaderboard
Ranked by agentic benchmark scores from Artificial Analysis.
| Rank | Model | Creator | Score | Input / 1M | Context | Last verified |
|---|---|---|---|---|---|---|
| 1 | GPT-5.6 Sol | OpenAI | 54.0 | $5.000 | 1.05M | Jul 12, 2026 |
| 2 | Claude Fable 5 | Anthropic | 52.8 | $10.000 | 1M | Jul 12, 2026 |
| 3 | GPT-5.6 Terra | OpenAI | 47.4 | $2.500 | 1.05M | Jul 12, 2026 |
| 4 | Anthropic: Claude Opus 4.8 | Anthropic | 47.2 | $5.000 | 1M | Jul 12, 2026 |
| 5 | Claude Sonnet 5 | Anthropic | 46.7 | $2.000 | 1M | Jul 12, 2026 |
| 6 | xAI: Grok 4.5 | xAI | 45.7 | $2.000 | 500K | Jul 12, 2026 |
| 7 | GPT-5.6 Luna | OpenAI | 45.6 | $1.000 | 1.05M | Jul 12, 2026 |
| 8 | GPT-5.5 | OpenAI | 44.9 | $5.000 | 1.05M | Jul 12, 2026 |
| 9 | Anthropic: Claude Opus 4.7 | Anthropic | 44.4 | $5.000 | 1M | Jul 12, 2026 |
| 10 | Z.ai: GLM 5.2 | Z Ai | 43.1 | $0.420 | 1.04858M | Jul 12, 2026 |
| 11 | GPT-5.4 | OpenAI | 41.1 | $2.500 | 1.05M | Jul 12, 2026 |
| 12 | Anthropic: Claude Sonnet 4.6 | Anthropic | 40.8 | $3.000 | 1M | Jul 12, 2026 |
| 13 | Gemini 3.5 Flash | 37.4 | $1.500 | 1.04858M | Jul 12, 2026 | |
| 14 | DeepSeek V4 Pro | DeepSeek | 36.4 | $0.435 | 1M | Jul 12, 2026 |
| 15 | MiniMax: MiniMax M3 | MiniMax | 35.4 | $0.300 | 1M | Jul 12, 2026 |
| 16 | DeepSeek V4 Flash | DeepSeek | 31.1 | $0.140 | 1M | Jul 12, 2026 |
| 17 | Qwen: Qwen3.7 Max | Alibaba Qwen | 30.6 | $1.250 | 1M | Jul 12, 2026 |
| 18 | Kimi K2.6 | Moonshot AI | 30.3 | $0.950 | 262.144K | Jul 12, 2026 |
| 19 | GPT-5.4 mini | OpenAI | 30.2 | $0.750 | 400K | Jul 12, 2026 |
| 20 | Z.ai: GLM 5.1 | Z Ai | 29.9 | $0.966 | 200K | Jul 12, 2026 |
| 21 | Kimi K2.7 Code | Moonshot AI | 29.6 | $0.950 | 262.144K | Jul 12, 2026 |
| 22 | MiMo-V2.5-Pro | Xiaomi | 29.1 | $0.435 | 1.04858M | Jul 12, 2026 |
| 23 | xAI: Grok Build 0.1 | xAI | 28.0 | $1.000 | 256K | Jul 12, 2026 |
| 24 | Qwen: Qwen3.6 Plus | Alibaba Qwen | 27.6 | $0.325 | 1M | Jul 12, 2026 |
| 25 | GPT-5.4 nano | OpenAI | 27.5 | $0.200 | 400K | Jul 12, 2026 |
| 26 | NVIDIA: Nemotron 3 Ultra (free) | NVIDIA | 27.4 | $0.000 | 1M | Jul 12, 2026 |
| 27 | Nemotron 3 Ultra 550B A55B | NVIDIA | 27.4 | $0.500 | 1M | Jul 12, 2026 |
| 28 | Qwen: Qwen3.6 27B | Alibaba Qwen | 27.0 | $0.285 | 262.14K | Jul 12, 2026 |
| 29 | GPT-5 | OpenAI | 25.7 | $1.250 | 400K | Jul 12, 2026 |
| 30 | MiniMax: MiniMax M2.7 | MiniMax | 25.6 | $0.240 | 196.608K | Jul 12, 2026 |
| 31 | Z.ai: GLM 4.7 | Z Ai | 25.4 | $0.400 | 202.752K | Jul 12, 2026 |
| 32 | Anthropic: Claude Sonnet 4.5 | Anthropic | 24.6 | $3.000 | 1M | Jul 12, 2026 |
| 33 | xAI: Grok 4.3 | xAI | 24.1 | $1.250 | 1M | Jul 12, 2026 |
| 34 | MiMo-V2.5 | Xiaomi | 23.7 | $0.140 | 1.04858M | Jul 12, 2026 |
| 35 | Step 3.7 Flash | StepFun | 21.5 | $0.200 | 256K | Jul 12, 2026 |
| 36 | Qwen: Qwen3.6 35B A3B | Alibaba Qwen | 21.4 | $0.140 | 262.144K | Jul 12, 2026 |
| 37 | Gemini 3.1 Pro Preview | 21.4 | $2.000 | 1.04858M | Jul 12, 2026 | |
| 38 | GPT-5.1 | OpenAI | 21.0 | $1.250 | 400K | Jul 12, 2026 |
| 39 | Qwen: Qwen3.7 Plus | Alibaba Qwen | 20.8 | $0.320 | 1M | Jul 12, 2026 |
| 40 | Qwen: Qwen3.5-122B-A10B | Alibaba Qwen | 20.7 | $0.260 | 262.144K | Jul 12, 2026 |
| 41 | Qwen: Qwen3.5 397B A17B | Alibaba Qwen | 19.8 | $0.385 | 131.072K | Jul 12, 2026 |
| 42 | GPT-5 Mini | OpenAI | 19.4 | $0.250 | 400K | Jul 12, 2026 |
| 43 | Mistral: Mistral Medium 3.5 | Mistral AI | 19.0 | $1.500 | 262.144K | Jul 12, 2026 |
| 44 | inclusionAI: Ring-2.6-1T | Inclusionai | 18.9 | $0.075 | 262.144K | Jul 12, 2026 |
| 45 | DeepSeek: DeepSeek V3.2 | DeepSeek | 18.3 | $0.214 | 128K | Jul 12, 2026 |
| 46 | DeepSeek: DeepSeek V3.1 Terminus | DeepSeek | 18.1 | $0.270 | 163.84K | Jul 12, 2026 |
| 47 | Z.ai: GLM 4.6 | Z Ai | 17.7 | $0.430 | 202.752K | Jul 12, 2026 |
| 48 | Anthropic: Claude Sonnet 4 | Anthropic | 16.6 | $3.000 | 1M | Jul 12, 2026 |
| 49 | Anthropic: Claude Haiku 4.5 | Anthropic | 16.4 | $1.000 | 200K | Jul 12, 2026 |
| 50 | Google: Gemma 4 31B (free) | 14.4 | $0.000 | 262.144K | Jul 12, 2026 | |
| 51 | Gemma 4 31B IT | 14.4 | $0.100 | 262.144K | Jul 12, 2026 | |
| 52 | OpenAI: gpt-oss-120b (free) | OpenAI | 13.2 | $0.000 | 131.072K | Jul 12, 2026 |
| 53 | GPT OSS 120B | OpenAI | 13.2 | $0.036 | 131.072K | Jul 12, 2026 |
| 54 | Google: Gemma 4 26B A4B (free) | 11.0 | $0.000 | 131.072K | Jul 12, 2026 | |
| 55 | Gemma 4 26B A4B IT | 11.0 | $0.060 | 262.144K | Jul 12, 2026 | |
| 56 | Mistral: Devstral 2 2512 | Mistral AI | 10.6 | $0.400 | 262.144K | Jul 12, 2026 |
| 57 | Cohere: Command A | Cohere | 9.2 | $2.500 | 256K | Jul 12, 2026 |
| 58 | Qwen: Qwen3 Coder Next | Alibaba Qwen | 8.8 | $0.110 | 262.144K | Jul 12, 2026 |
| 59 | NVIDIA: Nemotron 3 Super (free) | NVIDIA | 8.7 | $0.000 | 262.144K | Jul 12, 2026 |
| 60 | Nemotron 3 Super 120B A12B | NVIDIA | 8.7 | $0.200 | 262.144K | Jul 12, 2026 |
| 61 | Qwen: Qwen3.5-9B | Alibaba Qwen | 7.4 | $0.100 | 262.144K | Jul 12, 2026 |
| 62 | Gemini 2.5 Pro | 7.1 | $1.250 | 1.04858M | Jul 12, 2026 | |
| 63 | Mistral: Mistral Medium 3.1 | Mistral AI | 6.2 | $0.400 | 131.072K | Jul 12, 2026 |
| 64 | Gemini 3.1 Flash Lite Preview | 6.2 | $0.250 | 1.04858M | Jul 12, 2026 | |
| 65 | Mistral: Mistral Large 3 2512 | Mistral AI | 5.5 | $0.500 | 262.144K | Jul 12, 2026 |
| 66 | Mistral: Mistral Small 4 | Mistral AI | 4.7 | $0.150 | 262.144K | Jul 12, 2026 |
| 67 | Qwen: Qwen3 235B A22B Thinking 2507 | Alibaba Qwen | 3.8 | $0.150 | 131.072K | Jul 12, 2026 |
| 68 | OpenAI: gpt-oss-20b (free) | OpenAI | 3.1 | $0.000 | 131.072K | Jul 12, 2026 |
| 69 | DeepSeek-R1 | DeepSeek | 3.1 | $0.700 | 128K | Jul 12, 2026 |
| 70 | Amazon: Nova 2 Lite | Amazon | 3.1 | $0.300 | 1M | Jul 12, 2026 |
| 71 | GPT OSS 20B | OpenAI | 3.1 | $0.029 | 131.072K | Jul 12, 2026 |
| 72 | Upstage: Solar Pro 3 | Upstage | 2.7 | $0.150 | 128K | Jul 12, 2026 |
| 73 | inclusionAI: Ling-2.6-flash | Inclusionai | 2.3 | $0.010 | 262.144K | Jul 12, 2026 |
| 74 | Mistral: Ministral 3 14B 2512 | Mistral AI | 2.2 | $0.200 | 262.144K | Jul 12, 2026 |
| 75 | Qwen: Qwen3 Next 80B A3B Thinking | Alibaba Qwen | 2.1 | $0.098 | 131.072K | Jul 12, 2026 |
| 76 | Nemotron 3 Nano 30B A3B | NVIDIA | 2.0 | $0.050 | 262.144K | Jul 12, 2026 |
| 77 | NVIDIA: Nemotron 3 Nano 30B A3B (free) | NVIDIA | 2.0 | $0.000 | 256K | Jul 12, 2026 |
| 78 | Qwen: Qwen3 32B | Alibaba Qwen | 1.8 | $0.080 | 40.96K | Jul 12, 2026 |
| 79 | Qwen: Qwen3 30B A3B Thinking 2507 | Alibaba Qwen | 1.8 | $0.130 | 81.92K | Jul 12, 2026 |
| 80 | Qwen: Qwen3 14B | Alibaba Qwen | 1.8 | $0.100 | 40.96K | Jul 12, 2026 |
| 81 | Kimi K2 Thinking | Moonshot AI | 1.8 | $0.600 | 262.144K | Jul 12, 2026 |
| 82 | GPT-4.1 mini | OpenAI | 1.7 | $0.400 | 1.04758M | Jul 12, 2026 |
| 83 | OpenAI: o3 Mini High | OpenAI | 1.7 | $1.100 | 200K | Jul 12, 2026 |
| 84 | Mistral: Ministral 3 3B 2512 | Mistral AI | 1.6 | $0.100 | 131.072K | Jul 12, 2026 |
| 85 | Qwen: Qwen3 8B | Alibaba Qwen | 1.5 | $0.117 | 131.072K | Jul 12, 2026 |
| 86 | DeepSeek: DeepSeek V3 0324 | DeepSeek | 1.5 | $0.240 | 163.84K | Jul 12, 2026 |
| 87 | Meta: Llama 4 Maverick | Meta | 1.3 | $0.150 | 1.04858M | Jul 12, 2026 |
| 88 | Mistral: Ministral 3 8B 2512 | Mistral AI | 1.2 | $0.150 | 262.144K | Jul 12, 2026 |
| 89 | GPT-4.1 nano | OpenAI | 1.2 | $0.100 | 1.04758M | Jul 12, 2026 |
| 90 | Meta: Llama 4 Scout | Meta | 1.1 | $0.100 | 327.68K | Jul 12, 2026 |
| 91 | GPT-4o mini | OpenAI | 1.0 | $0.150 | 128K | Jul 12, 2026 |
| 92 | Meta: Llama 3.1 8B Instruct | Meta | 0.5 | $0.020 | 131.072K | Jul 12, 2026 |
| 93 | Meta: Llama 3.3 70B Instruct | Meta | 0.3 | $0.100 | 131.072K | Jul 12, 2026 |
| 94 | Google: Gemma 3 12B | 0.3 | $0.050 | 131.072K | Jul 12, 2026 | |
| 95 | Google: Gemma 3 27B | 0.3 | $0.080 | 131.072K | Jul 12, 2026 | |
| 96 | Meta: Llama 3.3 70B Instruct (free) | Meta | 0.3 | $0.000 | 65.536K | Jul 12, 2026 |