AI Agents
Models optimised for autonomous agent workflows.
| # | Model | Score | AI Index | Context | Input / 1M | Output / 1M | Caps | |
|---|---|---|---|---|---|---|---|---|
| 1 | Google: Gemini 3.1 Pro Previewgoogle Top Pick | 95.3 | 57.2 | 1M | $2.00 | $12.00 | TV | |
| 2 | Anthropic: Claude Opus 4.6anthropic Best for Coding In-House Pick | 94.2 | 53 | 1M | $5.00 | $25.00 | TV | |
| 3 | OpenAI: GPT-5.3-Codexopenai Top Pick | 91 | 53.6 | 400K | $1.75 | $14.00 | TV | |
| 4 | Anthropic: Claude Sonnet 4.6anthropic In-House Pick | 86.6 | 51.7 | 1M | $3.00 | $15.00 | TV | |
| 5 | Google: Gemini 3 Flash Previewgoogle | 84.1 | 46.4 | 1M | $0.5000 | $3.00 | TV | |
| 6 | OpenAI: GPT-5.1openai | 83.4 | 47.7 | 400K | $1.25 | $10.00 | TV | |
| 7 | Anthropic: Claude Opus 4.5anthropic | 83.3 | 49.7 | 200K | $5.00 | $25.00 | TV | |
| 8 | xAI: Grok 4.20x-ai New | 82.9 | 49.3 | 2M | $2.00 | $6.00 | TV | |
| 9 | xAI: Grok 4.20 Multi-Agent Betax-ai | 82.7 | 48.5 | 2M | $2.00 | $6.00 | TV | |
| 10 | OpenAI: GPT-5.2-Codexopenai | 81.6 | 49 | 400K | $1.75 | $14.00 | TV | |
| 11 | Xiaomi: MiMo-V2-Proxiaomi New | 81.5 | 49.2 | 1M | $1.00 | $3.00 | T | |
| 12 | Google: Nano Banana Pro (Gemini 3 Pro Image Preview)google | 80.4 | 48.4 | 66K | $2.00 | $12.00 | V | |
| 13 | MiniMax: MiniMax M2.7minimax New Top Pick | 79.6 | 49.6 | 197K | $0.3000 | $1.20 | T | |
| 14 | OpenAI: GPT-5 Codexopenai | 79.1 | 44.6 | 400K | $1.25 | $10.00 | TV | |
| 15 | Z.ai: GLM 5z-ai | 77.7 | 40.6 | 80K | $0.7200 | $2.30 | T | |
| 16 | Google: Gemini 3 Pro Previewgoogle | 77.6 | 41.3 | 1M | $2.00 | $12.00 | TV | |
| 17 | OpenAI: GPT-5openai | 77.6 | 23.9 | 400K | $1.25 | $10.00 | TV | |
| 18 | Kwaipilot: KAT-Coder-Pro V2kwaipilot New Best for Agents | 77.2 | 43.8 | 256K | $0.3000 | $1.20 | T | |
| 19 | Google: Gemini 2.5 Pro Preview 06-05google | 77.1 | 30.3 | 1M | $1.25 | $10.00 | TV | |
| 20 | Anthropic: Claude Opus 4.1anthropic | 76.9 | 42 | 200K | $15.00 | $75.00 | TV | |
| 21 | Google: Gemma 4 31Bgoogle New | 76.8 | 39.2 | 262K | $0.1300 | $0.3800 | TV | |
| 22 | OpenAI: GPT-5.1-Codexopenai | 76.5 | 43.1 | 400K | $1.25 | $10.00 | TV | |
| 23 | Anthropic: Claude Sonnet 4.5anthropic | 76.3 | 43 | 1M | $3.00 | $15.00 | TV | |
| 24 | OpenAI: GPT-5 Miniopenai | 76.3 | 41.2 | 400K | $0.2500 | $2.00 | TV | |
| 25 | Anthropic: Claude Opus 4anthropic | 74.9 | 39 | 200K | $15.00 | $75.00 | TV | |
| 26 | OpenAI: o3openai | 74.8 | 38.4 | 200K | $2.00 | $8.00 | TV | |
| 27 | Xiaomi: MiMo-V2-Omnixiaomi New | 74.7 | 43.4 | 262K | $0.4000 | $2.00 | TV | |
| 28 | Z.ai: GLM 5 Turboz-ai | 74.6 | 46.8 | 203K | $1.20 | $4.00 | T | |
| 29 | OpenAI: GPT-5.1-Codex-Miniopenai | 74.4 | 38.6 | 400K | $0.2500 | $2.00 | TV | |
| 30 | Z.ai: GLM 4.7z-ai | 74.1 | 34.2 | 203K | $0.3900 | $1.75 | T | |
| 31 | OpenAI: GPT-5.4 Nanoopenai New | 74.1 | 24.4 | 400K | $0.2000 | $1.25 | TV | |
| 32 | MiniMax: MiniMax M2.5minimax | 73.5 | 41.9 | 197K | $0.1180 | $0.9900 | T | |
| 33 | xAI: Grok 4x-ai | 73.3 | 41.5 | 256K | $3.00 | $15.00 | TV | |
| 34 | Qwen: Qwen3.5-122B-A10Bqwen | 72.9 | 35.9 | 262K | $0.2600 | $2.08 | TV | |
| 35 | Qwen: Qwen3.5 397B A17Bqwen | 72.7 | 40.1 | 262K | $0.3900 | $2.34 | TV | |
| 36 | OpenAI: GPT-5.4 Miniopenai New Best for Coding | 72.5 | 48.9 | 400K | $0.7500 | $4.50 | TV | |
| 37 | Qwen: Qwen3.5-27Bqwen | 72.4 | 37.2 | 262K | $0.1950 | $1.56 | TV | |
| 38 | Z.ai: GLM 5V Turboz-ai New | 72 | 42.9 | 203K | $1.20 | $4.00 | TV | |
| 39 | OpenAI: o3 Deep Researchopenai | 71.8 | 38.3 | 200K | $10.00 | $40.00 | TV | |
| 40 | Google: Gemini 2.5 Progoogle | 71.5 | 34.6 | 1M | $1.25 | $10.00 | TV | |
| 41 | MiniMax: MiniMax M2.1minimax | 70.8 | 39.4 | 197K | $0.2900 | $0.9500 | T | |
| 42 | MoonshotAI: Kimi K2 Thinkingmoonshotai | 70.6 | 40.9 | 262K | $0.6000 | $2.50 | T | |
| 43 | Anthropic: Claude Sonnet 4anthropic | 70.5 | 38.7 | 1M | $3.00 | $15.00 | TV | |
| 44 | Anthropic: Claude 3.7 Sonnet (thinking)anthropic | 69.6 | 34.7 | 200K | $3.00 | $15.00 | TV | |
| 45 | StepFun: Step 3.5 Flashstepfun Best Value | 68.7 | 37.8 | 262K | $0.1000 | $0.3000 | T | |
| 46 | MiniMax: MiniMax M2minimax | 68.5 | 36.1 | 197K | $0.2550 | $1.00 | T | |
| 47 | NVIDIA: Nemotron 3 Supernvidia | 66.7 | 36 | 262K | $0.1000 | $0.5000 | T | |
| 48 | DeepSeek: DeepSeek V3.2deepseek | 66.3 | 41.7 | 164K | $0.2600 | $0.3800 | T | |
| 49 | Anthropic: Claude 3.7 Sonnetanthropic | 65.9 | 30.8 | 200K | $3.00 | $15.00 | TV | |
| 50 | Kwaipilot: KAT-Coder-Pro V1kwaipilot | 64.5 | 36 | 256K | $0.2070 | $0.8280 | T |
#1Top Pick95.3
Google: Gemini 3.1 Pro Previewgoogle
Tool UseVision
#2Best for CodingIn-House Pick94.2
Anthropic: Claude Opus 4.6anthropic
Tool UseVision
#3Top Pick91
OpenAI: GPT-5.3-Codexopenai
Tool UseVision
#4In-House Pick86.6
Anthropic: Claude Sonnet 4.6anthropic
Tool UseVision
#584.1
Google: Gemini 3 Flash Previewgoogle
Tool UseVision
#683.4
OpenAI: GPT-5.1openai
Tool UseVision
#783.3
Anthropic: Claude Opus 4.5anthropic
Tool UseVision
#8New82.9
xAI: Grok 4.20x-ai
Tool UseVision
#982.7
xAI: Grok 4.20 Multi-Agent Betax-ai
Tool UseVision
#1081.6
OpenAI: GPT-5.2-Codexopenai
Tool UseVision
#11New81.5
Xiaomi: MiMo-V2-Proxiaomi
Tool Use
#1280.4
Google: Nano Banana Pro (Gemini 3 Pro Image Preview)google
Vision
#13NewTop Pick79.6
MiniMax: MiniMax M2.7minimax
Tool Use
#1479.1
OpenAI: GPT-5 Codexopenai
Tool UseVision
#1577.7
Z.ai: GLM 5z-ai
Tool Use
#1677.6
Google: Gemini 3 Pro Previewgoogle
Tool UseVision
#1777.6
OpenAI: GPT-5openai
Tool UseVision
#18NewBest for Agents77.2
Kwaipilot: KAT-Coder-Pro V2kwaipilot
Tool Use
#1977.1
Google: Gemini 2.5 Pro Preview 06-05google
Tool UseVision
#2076.9
Anthropic: Claude Opus 4.1anthropic
Tool UseVision
#21New76.8
Google: Gemma 4 31Bgoogle
Tool UseVision
#2276.5
OpenAI: GPT-5.1-Codexopenai
Tool UseVision
#2376.3
Anthropic: Claude Sonnet 4.5anthropic
Tool UseVision
#2476.3
OpenAI: GPT-5 Miniopenai
Tool UseVision
#2574.9
Anthropic: Claude Opus 4anthropic
Tool UseVision
#2674.8
OpenAI: o3openai
Tool UseVision
#27New74.7
Xiaomi: MiMo-V2-Omnixiaomi
Tool UseVision
#2874.6
Z.ai: GLM 5 Turboz-ai
Tool Use
#2974.4
OpenAI: GPT-5.1-Codex-Miniopenai
Tool UseVision
#3074.1
Z.ai: GLM 4.7z-ai
Tool Use
#31New74.1
OpenAI: GPT-5.4 Nanoopenai
Tool UseVision
#3273.5
MiniMax: MiniMax M2.5minimax
Tool Use
#3373.3
xAI: Grok 4x-ai
Tool UseVision
#3472.9
Qwen: Qwen3.5-122B-A10Bqwen
Tool UseVision
#3572.7
Qwen: Qwen3.5 397B A17Bqwen
Tool UseVision
#36NewBest for Coding72.5
OpenAI: GPT-5.4 Miniopenai
Tool UseVision
#3772.4
Qwen: Qwen3.5-27Bqwen
Tool UseVision
#38New72
Z.ai: GLM 5V Turboz-ai
Tool UseVision
#3971.8
OpenAI: o3 Deep Researchopenai
Tool UseVision
#4071.5
Google: Gemini 2.5 Progoogle
Tool UseVision
#4170.8
MiniMax: MiniMax M2.1minimax
Tool Use
#4270.6
MoonshotAI: Kimi K2 Thinkingmoonshotai
Tool Use
#4370.5
Anthropic: Claude Sonnet 4anthropic
Tool UseVision
#4469.6
Anthropic: Claude 3.7 Sonnet (thinking)anthropic
Tool UseVision
#45Best Value68.7
StepFun: Step 3.5 Flashstepfun
Tool Use
#4668.5
MiniMax: MiniMax M2minimax
Tool Use
#4766.7
NVIDIA: Nemotron 3 Supernvidia
Tool Use
#4866.3
DeepSeek: DeepSeek V3.2deepseek
Tool Use
#4965.9
Anthropic: Claude 3.7 Sonnetanthropic
Tool UseVision
#5064.5
Kwaipilot: KAT-Coder-Pro V1kwaipilot
Tool Use