Agentic AI Model Rankings
| # | Model | Agentic | Cost |
|---|---|---|---|
| 1 | GPT 5.6 Sol OpenAI | 88.8 | $11.25/M |
| 2 | Kimi K3 MoonshotAI | 88.3 | $6.00/M |
| 3 | GPT 5.6 Terra OpenAI | 87.4 | $5.63/M |
| 4 | GPT 5.6 Luna OpenAI | 84.7 | $2.25/M |
| 5 | Grok 4.5 xAI | 83.3 | $3.00/M |
| 6 | GPT 5.5 OpenAI | 82.7 | $11.25/M |
| 7 | Gemini 3.1 Pro Google | 80.2 | $4.50/M |
| 8 | Muse Spark 1.1 Meta Superintelligence Labs | 80.0 | $2.00/M |
| 9 | GPT 5.3 Codex OpenAI | 78.4 | $4.81/M |
| 10 | Gemini 3.6 FlashNew Google | 78.0 | $3.00/M |
| 11 | Claude Opus 4.6 Anthropic | 69.9 | $10.00/M |
| 12 | Qwen3.7 Max Qwen | 69.7 | $2.21/M |
| 13 | Gemini 3 Pro Google | 69.4 | — |
| 14 | GPT 5.2 Codex OpenAI | 66.5 | $4.81/M |
| 15 | GPT 5.2 OpenAI | 64.9 | $4.81/M |
| 16 | Gemini 3 Flash Google | 64.3 | $1.13/M |
| 17 | InklingNew Thinking Machines Lab | 63.8 | $1.76/M |
| 18 | Claude Opus 4.5 Anthropic | 63.1 | $10.00/M |
| 19 | GPT 5.1 Codex Mini OpenAI | 61.6 | $0.69/M |
| 20 | GPT 5.1 Codex Max OpenAI | 60.4 | $3.44/M |
| 21 | Grok 4.20 xAI | 57.3 | $1.56/M |
| 22 | Claude Sonnet 4.6 Anthropic | 53.4 | $6.00/M |
| 23 | GLM 5 Zhipu AI | 52.4 | $1.35/M |
| 24 | GPT 5 OpenAI | 49.6 | $3.44/M |
| 25 | GPT 5.1 OpenAI | 47.6 | $3.44/M |
| 26 | MiniMax M2.7 MiniMax | 45.1 | $0.44/M |
| 27 | GPT 5 Codex OpenAI | 44.3 | $3.44/M |
| 28 | Kimi K2.5 MoonshotAI | 43.2 | $1.14/M |
| 29 | Claude Sonnet 4.5 Anthropic | 42.8 | $6.00/M |
| 30 | MiniMax M2.5 MiniMax | 42.7 | $0.34/M |
| 31 | Claude Opus 4.1 Anthropic | 38.0 | $30.00/M |
| 32 | MiniMax M2.1 MiniMax | 36.6 | $0.52/M |
| 33 | Kimi K2 MoonshotAI | 35.7 | $1.00/M |
| 34 | GLM 4.7 Zhipu AI | 33.4 | $0.74/M |
| 35 | Gemini 2.5 Pro Google | 32.6 | $3.44/M |
| 36 | GPT 5 Mini OpenAI | 31.9 | $0.69/M |
| 37 | MiniMax M2 MiniMax | 30.0 | $0.52/M |
| 38 | Claude Haiku 4.5 Anthropic | 29.8 | $2.00/M |
| 39 | Grok Code Fast 1 xAI | 25.8 | — |
| 40 | GLM 4.6 Zhipu AI | 24.5 | $0.88/M |
| 41 | GPT Mini (120b) OpenAI | 18.7 | $0.07/M |
| 42 | Gemini 2.5 Flash Google | 17.1 | $0.85/M |
| 43 | GPT 5 Nano OpenAI | 11.5 | $0.14/M |
| 44 | Qwen3.5 9B Qwen | 9.2 | $0.11/M |
| 45 | GPT OSS 20B OpenAI | 3.4 | $0.06/M |
45 of 45 models, ranked by Terminal-Bench