Live data
Assembling the frontier
Ranking the latest models and provider endpoints.
Loading model dataLive data
Ranking the latest models and provider endpoints.
Loading model dataLive model ledger
Need methodology and scenario-specific picks? Read the dedicated agentic ai models guide.
Top overall
Claude Opus 5
QI 63.1
Best value
DeepSeek V4 Flash 0731
$0.05/M
Fastest
Celeris-1
2040 tok/s
Largest context
Llama 4 Scout
1.3M
| # | Model | Quality | Price/M | Speed | Context |
|---|---|---|---|---|---|
| 1 | Claude Opus 5Anthropic | 63.1 | $10.0 | 57 tok/s | 1.0M |
| 2 | GLM-5.3Z AI | 59.5 | $2.1 | 66 tok/s | 1.0M |
| 3 | Grok 4.6 (high)SpaceXAI | 60.9 | $3.0 | 60 tok/s | 500K |
| 4 | Grok 4.6 (xhigh)SpaceXAI | 60 | $3.0 | 60 tok/s | 500K |
| 5 | Grok 4.6 (medium)SpaceXAI | 59 | $3.0 | 58 tok/s | 500K |
| 6 | Grok 4.6 (low)SpaceXAI | 51.7 | $3.0 | 56 tok/s | 500K |
| 7 | Qwen3.8 MaxAlibaba | 58.1 | $3.0 | 26 tok/s | 1.0M |
| 8 | GLM-5.3-FlashZ AI | 57.5 | $0.12 | 297 tok/s | 1.0M |
| 9 | GPT-5.6 SolOpenAI | 60.9 | $8.0 | 114 tok/s | 1.0M |
| 10 | GPT-5.6 Sol (xhigh)OpenAI | 59 | $8.0 | 73 tok/s | 1.0M |
| 11 | GPT-5.6 Sol (high)OpenAI | 57.3 | $8.0 | 80 tok/s | 1.0M |
| 12 | GPT-5.6 Sol (medium)OpenAI | 55.6 | $8.0 | 72 tok/s | 1.0M |
| 13 | GPT-5.6 Sol (low)OpenAI | 50.7 | $8.0 | 70 tok/s | 1.0M |
| 14 | Qwen3.8 2.4T A95BAlibaba | 57.7 | $2.8 | 112 tok/s | 984K |
| 15 | Claude Fable 5Anthropic | 62.1 | $20.0 | 72 tok/s | 1.0M |
| 16 | Kimi K3Kimi | 59.7 | $5.1 | 167 tok/s | 1.0M |
| 17 | Kimi K3 (low)Kimi | 48.3 | $6.0 | 96 tok/s | 1.0M |
| 18 | DeepSeek V4 Flash VisionDeepSeek | 51.5 | $0.66 | 117 tok/s | 1.0M |
| 19 | Qwen3.8 27B (xhigh)Alibaba | 52 | $1.1 | 47 tok/s | 1.0M |
| 20 | Qwen3.8 27B (medium)Alibaba | 44.5 | $1.1 | 51 tok/s | 1.0M |
| 21 | Qwen3.8 27B (low)Alibaba | 42.9 | $1.1 | 51 tok/s | 1.0M |
| 22 | Qwen3.8 27BAlibaba | 34.7 | $1.1 | 51 tok/s | 1.0M |
| 23 | GPT-5.6 TerraOpenAI | 56.6 | $4.5 | 146 tok/s | 1.0M |
| 24 | GPT-5.6 Terra (xhigh)OpenAI | 52.8 | $4.5 | 103 tok/s | 1.0M |
| 25 | GPT-5.6 Terra (high)OpenAI | 50.1 | $4.5 | 98 tok/s | 1.0M |
| 26 | GPT-5.6 Terra (medium)OpenAI | 46.8 | $4.5 | 96 tok/s | 1.0M |
| 27 | GPT-5.6 Terra (low)OpenAI | 41.3 | $4.5 | 96 tok/s | 1.0M |
| 28 | Claude Sonnet 5Anthropic | 55.3 | $4.0 | 90 tok/s | 1.0M |
| 29 | DeepSeek V4 Pro 0813DeepSeek | 53.2 | $1.6 | 166 tok/s | 1.0M |
| 30 | Grok 4.5 (high)SpaceXAI | 55.8 | $3.0 | 50 tok/s | 500K |
Showing top 30 of 51 ranked models
View all in Explore →Decision routes
The overall score opens the conversation. These guides finish it with task-specific methodology and picks.
Ranking library
Focused rankings for the decisions engineers actually make.
Methodology
Every model is scored using the Artificial Analysis Intelligence Index — 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.
Field notes
Claude Opus 5 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.
DeepSeek V4 Flash 0731 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.
Celeris-1 leads on output speed right now at 2040 tokens/second. Speed matters most for real-time applications and agentic workflows with many sequential steps.
Llama 4 Scout has the biggest context window in this ranking at 1.3M. 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.