Models behind the plans
A plan is only as good as the models you can reach. Intelligence and cost per task come from the Artificial Analysis leaderboard, so a cheaper model that scores almost as high stretches every plan's allowance further.
Top intelligence
58
Claude Opus 5.5, $5.98/task
Best near-top value
52
GPT-6.1 Sol, $0.72/task
Cost per task ratio
8.3x
Opus 5.5 vs GPT-6.1 Sol, for 58 vs 52 on the index
[ Intelligence vs cost ]
Intelligence vs cost per task
Artificial Analysis Intelligence Index against what it costs to run their benchmark suite on that model. Up and to the left is better.
- Priced and tracked here
- Other models
[ Data ]
Model leaderboard
Source: Artificial Analysis LLM leaderboard, fetched 2026-10-08. "All-in $/1M out" is this site's reference agentic workload priced at the model's list prices (see Methodology); shown only where list prices are known.
| Model | Lab | ||||
|---|---|---|---|---|---|
| Claude Opus 5.5 (max with fallback) | Anthropic | 58 | $5.98 | 95 | $54 |
| Claude Sonnet 5.5 (max with fallback) | Anthropic | 56 | $5.46 | 129 | $27 |
| Claude Fable 5.1 (xhigh with fallback) | Anthropic | 53 | $5.98 | 58 | $125 |
| GPT-6 Astra (max) | OpenAI | 53 | $3.26 | 48 | $155 |
| Gemini 4 Argon (high) | 53 | $1.99 | n/a | n/a | |
| GPT-6.1 Sol (max) | OpenAI | 52 | $0.72 | 55 | $27 |
| Muse Spark 1.3 (max) | Meta | 48 | $1.60 | 209 | $18.38 |
| Grok 4.7 (high) | SpaceXAI | 46 | $2.73 | 78 | $39 |
| MiMo-V2.6-Pro | Xiaomi | 46 | $0.13 | 38 | n/a |
| Qwen3.8 Max (0902) | Alibaba | 45 | $5.41 | 37 | n/a |
| GLM-5.3 (max) | Z AI | 45 | $2.01 | 79 | n/a |
| Step 5 Preview | StepFun | 44 | $0.72 | 89 | n/a |
| Kimi K3 (max) | Kimi | 44 | $2 | 42 | n/a |
| Claude Haiku 5.5 (max) | Anthropic | 43 | $0.21 | 242 | $1.55 |
| GPT-5.6 Terra (max) | OpenAI | 42 | $1.40 | 108 | $33 |
| GLM-5.3-Flash | Z AI | 42 | $0.25 | 51 | n/a |
| Ling 3.1 Flash | InclusionAI | 41 | $0.99 | 211 | n/a |
| Gemini 3.8 Flash (high) | 41 | $1.24 | 125 | $11.38 | |
| Qwen3.8 2.4T A95B | Alibaba | 40 | $2.16 | 37 | n/a |
| Qwen3.8-Flash-Next | Alibaba | 40 | $0.37 | 56 | n/a |
| DeepSeek V4.1 Flash (max) | DeepSeek | 39 | $0.27 | 216 | n/a |
| Mistral Large 4 Preview | Mistral | 38 | $1.13 | 116 | n/a |
| GPT-6 Luna (max) | OpenAI | 38 | $0.07 | 129 | $1.55 |
| MiMo-V2.6-Flash | Xiaomi | 38 | $0.06 | 58 | n/a |
| DeepSeek V4 Pro 0813 (max) | DeepSeek | 36 | $0.67 | 100 | n/a |
| DeepSeek V4 Flash Vision (max) | DeepSeek | 35 | $0.31 | 220 | n/a |
| JT-4.1 Flash 236B A21B | China Mobile | 34 | n/a | n/a | n/a |
| Qwen3.8 27B (xhigh) | Alibaba | 34 | $1.01 | 47 | n/a |
| K2 Horizon 375B A23B | Institute of Foundation Models | 31 | $0 | 119 | n/a |
| Gemini 3.1 Pro Preview | 30 | $1.30 | 122 | $33 | |
| MiniMax-M3 | MiniMax | 29 | $0.51 | 94 | n/a |
| Quasar 438B (max) | Multiverse Computing | 27 | $2.02 | 126 | n/a |
| Apodex 1.1 | Apodex | 26 | $0.46 | n/a | n/a |
| GPT-5.5 Instant (June 2026) | OpenAI | 26 | $0.69 | 129 | n/a |
| Kimi K2.7 Code | Kimi | 26 | $0.54 | 84 | n/a |
| Inkling Small | Thinking Machines | 26 | $0.09 | 205 | n/a |
| K2 Horizon MoVA 36B A4B | Institute of Foundation Models | 25 | n/a | n/a | n/a |
| Hy3 | Tencent | 25 | $0.07 | 85 | n/a |
| Qwen3.7 Plus | Alibaba | 25 | $0.22 | 54 | n/a |
| Inkling (xhigh) | Thinking Machines | 25 | n/a | 151 | n/a |
| Ling-3.0-flash-VL | InclusionAI | 25 | n/a | 144 | n/a |
| Solar Mini 4 | Upstage | 24 | $0.36 | 79 | n/a |
| Nemotron 3 Ultra | NVIDIA | 23 | $0.60 | 155 | n/a |
| Ling-3.0-flash-Fin | InclusionAI | 23 | n/a | 322 | n/a |
| Gemini 3.5 Flash-Lite | 22 | $0.19 | 346 | n/a | |
| A.X-K2 | SK Telecom | 21 | n/a | n/a | n/a |
| K2 Horizon 7B | Institute of Foundation Models | 21 | n/a | n/a | n/a |
| LongCat 2.0 | LongCat | 19 | $0.06 | n/a | n/a |
| Qwen3.5 397B A17B | Alibaba | 18 | $0.47 | 90 | n/a |
| Qwen3.6 35B A3B | Alibaba | 18 | $0.48 | 133 | n/a |
| Muse Glimmer (high) | Meta | 17 | $0.06 | 89 | n/a |
| Claude 4.5 Haiku | Anthropic | 17 | $0.28 | 90 | n/a |
| Ring-2.6-1T | InclusionAI | 17 | $0.29 | 111 | n/a |
| K2 Horizon 3.7B | Institute of Foundation Models | 16 | n/a | n/a | n/a |
| Qwen3.5 122B A10B | Alibaba | 16 | $0.32 | 128 | n/a |
| Gemma 4 31B | 15 | $0 | 35 | n/a | |
| Mistral Medium 3.5 | Mistral | 14 | $0.50 | 168 | n/a |
| Command A+ | Cohere | 13 | $0 | 159 | n/a |
| Nemotron 3.5 Lightning | NVIDIA | 13 | $0.09 | 301 | n/a |
| Nemotron 3 Super | NVIDIA | 13 | $1.64 | 151 | n/a |
| MiniCPM5-2B | OpenBMB | 12 | n/a | n/a | n/a |
| Mercury 2.5 | Inception | 12 | $0.12 | 618 | n/a |
| gpt-oss-120b (high) | OpenAI | 12 | $0.11 | 183 | n/a |
| Mistral Small 4 | Mistral | 11 | $0.02 | 160 | n/a |
| Qwen3.5 9B | Alibaba | 11 | $0.21 | 59 | n/a |
| Granite 4.2 8B | IBM | 11 | $0.02 | 48 | n/a |
| Ling 3.0 Tiny | InclusionAI | 11 | $0 | 57 | n/a |
| Trinity Large Thinking | Arcee AI | 11 | $0.12 | 337 | n/a |
| North Mini Code | Cohere | 10 | $0 | 66 | n/a |
| Qwen3 Coder Next | Alibaba | 9 | $0.55 | 96 | n/a |
| Granite 4.2 3B | IBM | 9 | $0.01 | 214 | n/a |
| gpt-oss-20b (high) | OpenAI | 9 | $0.01 | 186 | n/a |
| Nemotron 3 Nano | NVIDIA | 9 | $0.02 | 190 | n/a |
| Celeris-1 | Celeris | 6 | $0.05 | 1498 | n/a |
| Ministral 3 14B | Mistral | 6 | $0.02 | 81 | n/a |
| Ministral 3 8B | Mistral | 5 | $0.01 | 101 | n/a |
| Ministral 3 3B | Mistral | 5 | $0.01 | 221 | n/a |
| Nemotron 3 Nano 4B | NVIDIA | 5 | n/a | n/a | n/a |
| K2 Horizon 0.9B | Institute of Foundation Models | 3 | n/a | n/a | n/a |