⥠Loading model data...
⥠Loading model data...
The top 30 models open-weight models ranked by quality. Updated live from Artificial Analysis data. Last updated: April 2026
Want the full deep dive? See the dedicated ai models for ollama guide.
Top overall
GLM-5.2
QI 51.1
Best value
gpt-oss-120b (high)
$0.07/M
Fastest
Gemma 4 31B
2126 tok/s
Largest context
Grok 4.20 0309 v2 (Reasoning)
2.0M
| # | Model | Quality | Price/M | Speed | Context |
|---|---|---|---|---|---|
| 1 | GLM-5.2Z AI | 51.1 | $1.3 | 455 tok/s | 1.0M |
| 2 | Muse Spark 1.1 (xhigh)Meta | 50.6 | $2.0 | 130 tok/s | 1.0M |
| 3 | Qwen3.7 MaxAlibaba | 46 | $1.9 | 197 tok/s | 1.0M |
| 4 | MiniMax-M3MiniMax | 44.4 | $0.52 | 118 tok/s | 1.0M |
| 5 | DeepSeek V4 ProDeepSeek | 44.3 | $0.54 | 225 tok/s | 1.0M |
| 6 | Kimi K2.6Kimi | 44.2 | $1.4 | 477 tok/s | 262K |
| 7 | MiMo-V2.5-ProXiaomi | 42.2 | $0.54 | 105 tok/s | 1.0M |
| 8 | Kimi K2.7 CodeKimi | 41.9 | $1.4 | 479 tok/s | 262K |
| 9 | Hy3Tencent | 41.2 | Free | 58 tok/s | 262K |
| 10 | Nex-N2-ProNex AGI | 41 | $1.0 | 140 tok/s | 262K |
| 11 | DeepSeek V4 FlashDeepSeek | 40.3 | $0.11 | 221 tok/s | 1.0M |
| 12 | GLM-5.1 (Reasoning)Z AI | 40.2 | $1.6 | 187 tok/s | 205K |
| 13 | Qwen3.6 Max PreviewAlibaba | 40 | $2.9 | 45 tok/s | 256K |
| 14 | Qwen3.6 PlusAlibaba | 39.6 | $1.1 | 53 tok/s | 1.0M |
| 15 | GLM-5 (Reasoning)Z AI | 39.5 | $0.97 | 191 tok/s | 203K |
| 16 | Qwen3.7 PlusAlibaba | 39 | $0.70 | 52 tok/s | 1.0M |
| 17 | MiniMax-M2.7MiniMax | 38.1 | $0.52 | 463 tok/s | 205K |
| 18 | Nemotron 3 Ultra 550B A55B (Reasoning)NVIDIA | 37.8 | $0.55 | 459 tok/s | 512K |
| 19 | MiMo-V2.5Xiaomi | 37.2 | $0.18 | 93 tok/s | 1.0M |
| 20 | Qwen3.6 27B (Reasoning)Alibaba | 37.1 | $1.0 | 480 tok/s | 262K |
| 21 | GLM-5.1Z AI | 35.4 | $1.6 | 169 tok/s | 205K |
| 22 | Kimi K2.5 (Reasoning)Kimi | 35.4 | $0.90 | 212 tok/s | 262K |
| 23 | Qwen3.5 27B (Reasoning)Alibaba | 33.8 | $0.69 | 106 tok/s | 262K |
| 24 | Qwen3.5 397B A17B (Reasoning)Alibaba | 33.7 | $0.88 | 112 tok/s | 262K |
| 25 | MiniMax-M2.5MiniMax | 33.7 | $0.39 | 142 tok/s | 205K |
| 26 | GLM-4.7 (Reasoning)Z AI | 33.7 | $0.74 | 1181 tok/s | 205K |
| 27 | Hy3-preview (Reasoning)Tencent | 33.6 | $0.11 | 157 tok/s | 256K |
| 28 | Kimi K2 ThinkingKimi | 32.7 | $1.1 | 249 tok/s | 262K |
| 29 | GLM-5Z AI | 32.4 | $0.97 | 86 tok/s | 203K |
| 30 | Qwen3.5 122B A10B (Reasoning)Alibaba | 32.3 | $0.72 | 140 tok/s | 262K |
Showing top 30 of 206 ranked models
View all in Explore âEach guide goes deeper than the quick filters, with methodology, benchmarks, and picks per scenario.
Model rankings
Browse the latest ranking pages for overall models, coding, open source, Ollama, long context, and agentic workflows.
Current coding leaderboard using LiveCodeBench, Terminal-Bench, and SciCode.
Top open-weight models for self-hosting, Ollama, and low-cost API use.
Best local AI models by hardware tier for self-hosting on Macs, RTX GPUs, and workstations.
Ollama-first picks for coding, chat, reasoning, and low-friction local inference.
Best long-context models for large documents, codebases, and retrieval-heavy workflows.
Rankings for tool use, multi-step execution, and autonomous agent workflows.
Every model is scored using the Artificial Analysis Intelligence Index â a composite of GPQA Diamond, AIME 2025, LiveCodeBench, MMLU-Pro, and other benchmarks, weighted into a single 0-100 quality score. Speed, price, and context window are tracked live across providers.
The overall ranking is a starting point. For production decisions, narrow by use case using the category pages above, then compare finalists head-to-head on Compare.
GLM-5.2 leads on overall quality right now, but the best model depends on your priorities. Coding, cost, speed, and context length all shift the answer. Use the category rankings above to find the right fit.
gpt-oss-120b (high) currently offers one of the best quality-to-cost ratios. Open-source models on providers like Groq or Together can be even cheaper at strong quality levels.
Start with overall quality index, then narrow by what matters for your workload: cost per million tokens, output speed, context window, or a specific capability like coding or tool use. Use our Compare tool to put finalists head to head.
Gemma 4 31B leads on output speed right now at 2126 tokens/second. Speed matters most for real-time applications and agentic workflows with many sequential steps.
Grok 4.20 0309 v2 (Reasoning) has the biggest context window in this ranking at 2.0M. For a dedicated long-context comparison, see our largest context window page.
Data is pulled from Artificial Analysis and refreshed automatically. New models appear as soon as they have benchmark scores and provider endpoints. The ranking reflects the live state of the leaderboard.