Choosing a model for your use case does not always mean choosing the highest score. Rule out what you cannot use, weight what you care about, and read why each model lands where it does. The ranking is deterministic: the same weights give the same list.
Open weights only · must not train on your data · a maximum blended price · a required region. These exclude models outright; only GA models are considered.
Four weights: Capability (SWE-bench Verified and GPQA Diamond, whichever the model publishes.); Price (Blended $ per 1M tokens at 3:1, lower is better, log-scaled.); Speed (Output tokens per second as cited from Artificial Analysis.); Data terms (Does not train on your data, documents a zero-data-retention option, states a retention period.). A model that does not publish a weighted figure is not ranked; set that weight to 0 to include it.
128 GA models pass the default constraints; 46 publish every weighted figure and are ranked here under the default weights (Capability 50 · Price 50 · Speed 0 · Data terms 25). Top ten:
| # | Model | Creator | Score | Why it sits here |
|---|---|---|---|---|
| 1 | Grok 4.6 | xAI | 78.1 | Rank 1 of 46: strong on capability (rank 5 of 46) and data terms (rank 1 of 46). |
| 2 | MiniMax M2.7 | MiniMax | 75.3 | Rank 2 of 46: strong on price (rank 10 of 46). |
| 3 | Gemini 3.1 Flash-Lite | Google DeepMind | 74.5 | Rank 3 of 46: strong on price (rank 14 of 46). |
| 4 | MiniMax M3 | MiniMax | 72.6 | Rank 4 of 46: strong on price (rank 10 of 46). |
| 5 | Muse Spark 1.3 | Meta AI | 72.2 | Rank 5 of 46: strong on capability (rank 7 of 46). |
| 6 | Grok 4.20 | xAI | 72.1 | Rank 6 of 46: strong on data terms (rank 1 of 46). |
| 7 | Qwen3.8-27B | Alibaba Cloud (Qwen Team) | 72 | Rank 7 of 46: mid-pack on every weighted axis. |
| 8 | Claude Opus 5 | Anthropic | 71.2 | Rank 8 of 46: strong on capability (rank 2 of 46) and data terms (rank 1 of 46), weaker on price (rank 36 of 46). |
| 9 | DeepSeek-V4.1-Flash | DeepSeek | 69.6 | Rank 9 of 46: strong on capability (rank 13 of 46) and price (rank 8 of 46), weaker on data terms (rank 38 of 46). |
| 10 | Solar Pro 4 | Upstage | 69.6 | Rank 10 of 46: strong on price (rank 10 of 46), weaker on capability (rank 33 of 46). |
Not ranked because a weighted figure is not published: Aion 3.5 (no capability); Amazon Nova 2.5 Sonic (no capability or data terms); Beam (no data terms); Bosun (no capability or price); ChatGPT Images 2.5 (no capability or price); Claude Fable 5.1 (no capability); Claude Haiku 5.5 (no capability); Claude Mythos 5.1 (no capability); Claude Opus 5.5 (no capability); Claude Sonnet 5.5 (no capability); Cohere Command A+ (no price); Cohere Parse 5 (no capability or price); DeepSeek-V4.1-Flash-1017 (no capability); DiffusionGemma 26B-A4B (no price); FLUX.2 (no capability or price); GLM-5.3 (no capability); GLM-5.3-Flash (no capability); GPT Image 2 (no capability); GPT-5.6-Cyber (no capability); GPT-6 Luna (no capability); GPT-6 Sol (no capability); GPT-6.1 Sol (no capability); Gemini 3 Pro Image (no capability); Gemini 3.6 Flash (no capability); Gemini 3.8 Flash (no capability); Gemini 3.8 Flash TTS (no capability); Gemini 3.8 Live (no capability); Gemini 4 Argon (no capability); Gemini Nano (no capability); Gemini Omni 1.1 Flash (no capability or data terms); Gemma 4 12B (no price); Gemma 4 31B (no price); Grok 4.3 (no capability or data terms); Grok 4.5 (no capability); Grok 4.7 (no capability); Grok Imagine Image 2.0 (no capability or price); HappyHorse 1.0 (no capability or price); HyperCLOVA X (no capability or price); Jev (no capability); K-EXAONE 2.0 (no price); Kanana-2 30B-A3B Instruct (no price); Kling 3.0 (no capability or price); Kolibri (no price); LFM2.5-VL-3B (no capability or price); LTX-2.5 (no capability or price); Ling 3.0 Flash Fin (no capability); MAI-Code-1.1-Flash (no data terms); MAI-Image-2.5 (no capability); Mellum2.1 (no price); Mercury 3 (no capability); MiMo-V2.6-Distill-Qwen-9B (no price); MiMo-V2.6-Flash (no capability or data terms); MiMo-V2.6-Flash-RL (no capability); MiMo-V2.6-Pro (no capability or data terms); MiMo-V2.6-Pro-RL (no capability); MiniMax H3 (no capability or price); MiniMax M3.1 Flash (no capability or data terms); MiniMax Music 3.0 (no capability or price); Ministral 3 3B (no capability); Mistral OCR 4 (no capability or price); Muse Glimmer (no price); Muse Spark Open (no price); Nano Banana 2.1 (no capability); Nemotron 3.5 Bolt 74B-A9B 24GB (no price); Nemotron Labs Dory 1.0 4B (no price); North Micro Vision Instruct (no capability); Olmo 3.1 32B Think (no price); Osmosis-Structure-0.6B (no capability or price or data terms); Pulsar 16B (no price); Qwen-Image-2.1 (no capability or price or data terms); Qwen3.6-27B (no price); Qwen3.7-Plus (no capability); Recraft V3 (no capability or price); Recraft V4.1 (no capability or price); Riverflow 2.0 Pro (no capability or price); Seed 2.1 Turbo (no capability); SeedRealtime (no capability or price); Seedance 2.5 (no capability or price or data terms); Strands Decider 2B (no capability or price); Suno V6 (no capability or price); Wan-Animate-2 (no capability or price); WeatherNext 3 (no capability or price).
Smart Match asks about your team and budget and returns a ranked stack with reasons. Open Smart Match · Full leaderboard · All models