TASK RANK
Agentic model rank
| # | Model | Agentic | Input / 1M | Output / 1M | Context |
|---|---|---|---|---|---|
| 01 | AnthropicClaude Opus 5 | 55.3 | $5.00 | $25 | 1M |
| 02 | OpenAIGPT-5.6 Sol | 54.0 | $5.00 | $30 | 1.1M |
| 03 | AnthropicClaude Fable 5 | 52.8 | $10 | $50 | 1M |
| 04 | Moonshot AIKimi K3 | 50.1 | $3.00 | $15 | 1.0M |
| 05 | OpenAIGPT-5.6 Terra | 47.4 | $2.50 | $15 | 1.1M |
| 06 | AnthropicClaude Opus 4.8 | 47.2 | $5.00 | $25 | 1M |
| 07 | AnthropicClaude Sonnet 5 | 46.7 | $2.00 | $10 | 1M |
| 08 | xAIGrok 4.5 | 45.7 | $2.00 | $6.00 | 500K |
| 09 | OpenAIGPT-5.6 Luna | 45.6 | $1.00 | $6.00 | 1.1M |
| 10 | OpenAIGPT-5.5 | 44.9 | $5.00 | $30 | 1.1M |
| 11 | AnthropicClaude Opus 4.7 | 44.4 | $5.00 | $25 | 1M |
| 12 | Z AiGLM 5.2 | 43.1 | $0.67 | $2.10 | 1.0M |
| 13 | OpenAIGPT-5.4 | 41.1 | $2.50 | $15 | 1.1M |
| 14 | AnthropicClaude Sonnet 4.6 | 40.8 | $3.00 | $15 | 1M |
| 15 | GoogleGemini 3.6 Flash | 38.7 | $1.50 | $7.50 | 1.0M |
| 16 | MetaMuse Spark 1.1 | 37.5 | $1.25 | $4.25 | 1.0M |
| 17 | GoogleGemini 3.5 Flash | 37.4 | $1.50 | $9.00 | 1.0M |
| 18 | DeepseekDeepSeek V4 Pro | 36.4 | $0.43 | $0.87 | 1.0M |
| 19 | MinimaxMiniMax M3 | 35.4 | $0.30 | $1.20 | 1.0M |
| 20 | ThinkingmachinesInkling | 32.3 | $1.00 | $4.05 | 1.0M |
| 21 | DeepseekDeepSeek V4 Flash | 31.1 | $0.14 | $0.28 | 1.0M |
| 22 | Nex AgiNex-N2-Pro | 31.0 | $0.25 | $1.00 | 262K |
| 23 | TencentHy3 preview | 30.7 | $0.06 | $0.21 | 262K |
| 24 | QwenQwen3.7 Max | 30.6 | $1.48 | $4.42 | 1M |
| 25 | Moonshot AIKimi K2.6 | 30.3 | $0.65 | $2.72 | 262K |
| 26 | OpenAIGPT-5.4 Mini | 30.2 | $0.75 | $4.50 | 400K |
| 27 | Z AiGLM 5.1 | 29.9 | $0.97 | $3.04 | 205K |
| 28 | Moonshot AIKimi K2.7 Code | 29.6 | $0.73 | $3.50 | 262K |
| 29 | XiaomiMiMo-V2.5-Pro | 29.1 | $0.43 | $0.87 | 1.1M |
| 30 | xAIGrok Build 0.1 | 28.0 | $1.00 | $2.00 | 256K |
| 31 | QwenQwen3.6 Plus | 27.6 | $0.33 | $1.95 | 1M |
| 32 | OpenAIGPT-5.4 Nano | 27.5 | $0.20 | $1.25 | 400K |
| 33 | NvidiaNemotron 3 Ultra | 27.4 | $0.60 | $3.60 | 512K |
| 34 | QwenQwen3.6 27B | 27.0 | $0.30 | $2.00 | 262K |
| 35 | GoogleGemini 3.5 Flash Lite | 26.8 | $0.30 | $2.50 | 1.0M |
| 36 | OpenAIGPT-5 | 25.7 | $1.25 | $10 | 400K |
| 37 | MinimaxMiniMax M2.7 | 25.6 | $0.25 | $1.00 | 205K |
| 38 | Z AiGLM 4.7 | 25.4 | $0.40 | $1.75 | 205K |
| 39 | AnthropicClaude Sonnet 4.5 | 24.6 | $3.00 | $15 | 1M |
| 40 | xAIGrok 4.3 | 24.1 | $1.25 | $2.50 | 1M |
| 41 | XiaomiMiMo-V2.5 | 23.7 | $0.14 | $0.28 | 1.1M |
| 42 | Moonshot AIKimi K2.5 | 21.7 | $0.57 | $2.85 | 262K |
| 43 | StepfunStep 3.7 Flash | 21.5 | $0.20 | $1.15 | 262K |
| 44 | GoogleGemini 3.1 Pro Preview | 21.4 | $2.00 | $12 | 1.0M |
| 45 | QwenQwen3.6 35B A3B | 21.4 | $0.14 | $1.00 | 262K |
| 46 | OpenAIGPT-5.1 | 21.0 | $1.25 | $10 | 400K |
| 47 | QwenQwen3.7 Plus | 20.8 | $0.32 | $1.28 | 1M |
| 48 | QwenQwen3.5-122B-A10B | 20.7 | $0.26 | $2.08 | 262K |
| 49 | QwenQwen3.5 397B A17B | 19.8 | $0.39 | $2.34 | 262K |
| 50 | OpenAIGPT-5 Mini | 19.4 | $0.25 | $2.00 | 400K |
| 51 | MistralMistral Medium 3.5 | 19.0 | $1.50 | $7.50 | 262K |
| 52 | InclusionaiRing-2.6-1T | 18.9 | $0.07 | $0.63 | 262K |
| 53 | DeepseekDeepSeek V3.2 | 18.3 | $0.27 | $0.40 | 164K |
| 54 | DeepseekDeepSeek V3.1 Terminus | 18.1 | $0.27 | $1.00 | 164K |
| 55 | Z AiGLM 4.6 | 17.7 | $0.50 | $2.00 | 205K |
| 56 | AnthropicClaude Sonnet 4 | 16.6 | $3.00 | $15 | 1M |
| 57 | AnthropicClaude Haiku 4.5 | 16.4 | $1.00 | $5.00 | 200K |
| 58 | KwaipilotKAT-Coder-Pro V2 | 15.5 | $0.30 | $1.20 | 262K |
| 59 | GoogleGemma 4 31B | 14.4 | $0.14 | $0.40 | 262K |
| 60 | OpenAIgpt-oss-120b | 13.2 | $0.04 | $0.17 | 131K |
| 61 | QwenQwen3.5-35B-A3B | 11.8 | $0.14 | $1.00 | 262K |
| 62 | GoogleGemma 4 26B A4B | 11.0 | $0.12 | $0.35 | 262K |
| 63 | MistralDevstral 2 2512 | 10.6 | $0.40 | $2.00 | 262K |
| 64 | InceptionMercury 2 | 9.6 | $0.25 | $0.75 | 128K |
| 65 | CohereCommand A | 9.2 | $2.50 | $10 | 256K |
| 66 | QwenQwen3 Coder Next | 8.8 | $0.11 | $0.80 | 262K |
| 67 | NvidiaNemotron 3 Super | 8.7 | $0.08 | $0.40 | 1M |
| 68 | QwenQwen3.5-9B | 7.4 | $0.10 | $0.15 | 262K |
| 69 | GoogleGemini 2.5 Pro | 7.1 | $1.25 | $10 | 1.0M |
| 70 | GoogleGemini 3.1 Flash Lite Preview | 6.2 | $0.25 | $1.50 | 1.0M |
| 71 | MistralMistral Medium 3.1 | 6.2 | $0.40 | $2.00 | 131K |
| 72 | MistralMistral Large 3 2512 | 5.5 | $0.50 | $1.50 | 262K |
| 73 | MistralMistral Small 4 | 4.7 | $0.15 | $0.60 | 262K |
| 74 | QwenQwen3 235B A22B Thinking 2507 | 3.8 | $0.30 | $3.00 | 262K |
| 75 | Arcee AiTrinity Large Thinking | 3.7 | $0.22 | $0.85 | 262K |
| 76 | DeepseekR1 | 3.1 | $0.70 | $2.50 | 164K |
| 77 | AmazonNova 2 Lite | 3.1 | $0.30 | $2.50 | 1M |
| 78 | OpenAIgpt-oss-20b | 3.1 | $0.03 | $0.14 | 131K |
| 79 | UpstageSolar Pro 3 | 2.7 | $0.15 | $0.60 | 128K |
| 80 | InclusionaiLing-2.6-flash | 2.3 | $0.01 | $0.03 | 262K |
| 81 | MistralMinistral 3 14B 2512 | 2.2 | $0.20 | $0.20 | 262K |
| 82 | QwenQwen3 Next 80B A3B Thinking | 2.1 | $0.10 | $0.78 | 262K |
| 83 | NvidiaNemotron 3 Nano 30B A3B | 2.0 | $0.05 | $0.20 | 262K |
| 84 | Moonshot AIKimi K2 Thinking | 1.8 | $0.60 | $2.50 | 262K |
| 85 | QwenQwen3 30B A3B Thinking 2507 | 1.8 | $0.13 | $1.56 | 82K |
| 86 | QwenQwen3 32B | 1.8 | $0.08 | $0.28 | 131K |
| 87 | QwenQwen3 14B | 1.8 | $0.23 | $0.91 | 131K |
| 88 | OpenAIo3 Mini High | 1.7 | $1.10 | $4.40 | 200K |
| 89 | OpenAIGPT-4.1 Mini | 1.7 | $0.40 | $1.60 | 1.0M |
| 90 | MistralMinistral 3 3B 2512 | 1.6 | $0.10 | $0.10 | 131K |
| 91 | DeepseekDeepSeek V3 0324 | 1.5 | $0.27 | $1.12 | 164K |
| 92 | QwenQwen3 8B | 1.5 | $0.12 | $0.45 | 131K |
| 93 | MetaLlama 4 Maverick | 1.3 | $0.20 | $0.80 | 1.0M |
| 94 | OpenAIGPT-4.1 Nano | 1.2 | $0.10 | $0.40 | 1.0M |
| 95 | MistralMinistral 3 8B 2512 | 1.2 | $0.15 | $0.15 | 262K |
| 96 | MetaLlama 4 Scout | 1.1 | $0.10 | $0.30 | 1.3M |
| 97 | MetaLlama 3.1 8B Instruct | 0.5 | $0.05 | $0.08 | 131K |
| 98 | MetaLlama 3.3 70B Instruct | 0.3 | $0.13 | $0.40 | 131K |
| 99 | GoogleGemma 3 27B | 0.3 | $0.08 | $0.45 | 262K |
| 100 | GoogleGemma 3 12B | 0.3 | $0.05 | $0.15 | 131K |