1Gemini 4 Carbon (High)Googleintelligence59.4Task $7.76Response 1.7 min1.0M context1 provider
Model discovery workbench
Move from a crowded market to a defensible shortlist. Rank models by capability, task economics, speed, context, and real provider availability.
- Models
- 162
- Providers
- 109
- Provider data fetched
- Oct 30, 2026, 02:53 UTC
- Method
- Index v5
- Newest release
- Oct 28, 2026
Model rankings
147 results · sorted by intelligence
| # | Details | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| 1 | Gemini 4 Carbon (High)Google | 59.4 | N/A | N/A | $7.76 | 1.7 min | 1.0M | 1 | |
| 2 | Claude Opus 5.5Anthropic | 58.4 | N/A | N/A | $0.976 | 10s | 1.0M | 4 | |
| 3 | GPT-6 AstraOpenAI | 56.9 | N/A | N/A | $6.24 | 4.5 min | 1.0M | 4 | |
| 4 | GPT-6 Astra (Xhigh)OpenAI | 55.3 | N/A | N/A | $3.66 | 2.2 min | 1.0M | 1 | |
| 5 | GPT-6 Astra (High)OpenAI | 54.8 | N/A | N/A | $3.24 | 41s | 1.0M | 1 | |
| 6 | GPT-6.1 SolOpenAI | 54.5 | N/A | N/A | $1.27 | 4.3 min | 1.0M | 5 | |
| 7 | Claude Sonnet 5.5Anthropic | 54.2 | N/A | N/A | $0.511 | 5.8s | 1.0M | 4 | |
| 8 | GPT-6.1 Sol (Xhigh)OpenAI | 52.3 | N/A | N/A | $0.764 | 1.7 min | 1.0M | 1 | |
| 9 | GPT-6 Astra (Medium)OpenAI | 51.5 | N/A | N/A | $2.73 | 11s | 1.0M | 1 | |
| 10 | GPT-6.1 TerraOpenAI | 51 | N/A | N/A | $0.226 | 6.5s | 1.0M | 1 | |
| 11 | Gemini 4 Argon (High)Google | 50.4 | N/A | N/A | $7.68 | 53s | 1.0M | 2 | |
| 12 | GPT-6.1 Sol (High)OpenAI | 50.2 | N/A | N/A | $0.591 | 38s | 1.0M | 1 | |
| 13 | Claude Fable 5.1Anthropic | 49.7 | N/A | N/A | $4.47 | 10s | 1.0M | 1 | |
| 14 | GPT-6.1 Sol (Medium)OpenAI | 46.1 | N/A | N/A | $0.359 | 12s | 1.0M | 1 | |
| 15 | Kimi K3.1 ProOpenKimi | 46 | N/A | N/A | $3.68 | 73s | 1.0M | 2 | |
| 16 | GPT-6.1 Terra (Xhigh)OpenAI | 45 | N/A | N/A | $0.401 | 32s | 1.0M | 1 | |
| 17 | Muse WonderOpenMeta | 43.3 | N/A | N/A | $6.95 | 36s | 1.0M | 1 | |
| 18 | GPT-6 Astra (Low)OpenAI | 43 | N/A | N/A | $1.42 | 11s | 1.0M | 2 | |
| 19 | GPT-6.1 Terra (High)OpenAI | 42.3 | N/A | N/A | $0.259 | 12s | 1.0M | 1 | |
| 20 | GPT-6.1 Terra (Medium)OpenAI | 38.1 | N/A | N/A | $0.169 | 7.6s | 1.0M | 1 | |
| 21 | Claude Haiku 5.5Anthropic | 36.2 | N/A | N/A | $0.411 | 5.7 min | 1.0M | 1 | |
| 22 | Grok 4.7 (High)SpaceXAI | 35 | N/A | N/A | $6.18 | 24s | 500K | 1 | |
| 23 | GPT-6.1 Sol (Low)OpenAI | 34.5 | N/A | N/A | $0.162 | 11s | 1.0M | 1 | |
| 24 | Claude Haiku 5.5 (Xhigh)Anthropic | 34.3 | N/A | N/A | $0.248 | 66s | 1.0M | 1 | |
| 25 | Grok 4.7 (Xhigh)SpaceXAI | 34.3 | N/A | N/A | $7.51 | 35s | 500K | 1 | |
| 26 | Qwen3.8 MaxOpenAlibaba | 33.6 | N/A | N/A | $10 | 64s | 984K | 1 | |
| 27 | DeepSeek V4.1 Flash 1017OpenDeepSeek | 32.5 | N/A | N/A | $0.602 | 15s | 1.0M | 21 | |
| 28 | GLM-5.3OpenZ AI | 31.7 | N/A | N/A | $5.01 | 36s | 1.0M | 26 | |
| 29 | Grok 4.7 (Low)SpaceXAI | 30.9 | N/A | N/A | $2.92 | 13s | 500K | 1 | |
| 30 | Gemini 3.8 Flash (High)Google | 30.5 | N/A | N/A | $7.77 | 29s | 1.0M | 1 | |
| 31 | MiMo-V2.6-ProOpenXiaomi | 29.9 | N/A | N/A | $0.257 | 46s | 1.0M | 4 | |
| 32 | Claude Haiku 5.5 (High)Anthropic | 29.6 | N/A | N/A | $0.159 | 18s | 1.0M | 1 | |
| 33 | GPT-6.1 Terra (Low)OpenAI | 29.2 | N/A | N/A | $0.071 | 6.8s | 1.0M | 1 | |
| 34 | MiniMax-M3.1-FlashOpenMiniMax | 28.9 | N/A | N/A | $0.491 | 22s | 1.0M | 12 | |
| 35 | Step 5 PreviewOpenStepFun | 28.5 | N/A | N/A | $2.35 | 15s | 1.0M | 1 | |
| 36 | GPT-6 LunaOpenAI | 27.8 | N/A | N/A | $0.071 | 5.2s | 1.0M | 3 | |
| 37 | MiMo-V2.6-FlashOpenXiaomi | 26.7 | N/A | N/A | $0.129 | 46s | 1.0M | 4 | |
| 38 | Mistral Large 4 PreviewOpenMistral | 25.3 | N/A | N/A | $5.54 | 24s | 524K | 1 | |
| 39 | Mistral Large 4 (High)OpenMistral | 25.3 | N/A | N/A | N/A | N/A | 1.0M | 1 | |
| 40 | Muse Spark Open (Xhigh)OpenMeta | 24.7 | N/A | N/A | $2.02 | 18s | 1.0M | 5 | |
| 41 | Claude Haiku 5.5 (Medium)Anthropic | 24.6 | N/A | N/A | $0.092 | 11s | 1.0M | 1 | |
| 42 | GPT-6 Luna (Xhigh)OpenAI | 23.3 | N/A | N/A | $0.104 | 21s | 1.0M | 1 | |
| 43 | DeepSeek V4 Pro 0813OpenDeepSeek | 23.1 | N/A | N/A | $1.77 | 8.1s | 1.0M | 10 | |
| 44 | GLM-5.3 (Low)OpenZ AI | 23.1 | N/A | N/A | $1.57 | 32s | 1.0M | 9 | |
| 45 | GPT-6 Luna (High)OpenAI | 21.4 | N/A | N/A | $0.073 | 16s | 1.0M | 1 | |
| 46 | Qwen3.8 27B (Xhigh)OpenAlibaba | 20.1 | N/A | N/A | $3.53 | 72s | 1.0M | 9 | |
| 47 | MiniMax-M3OpenMiniMax | 18.7 | N/A | N/A | $1.29 | 25s | 1.0M | 11 | |
| 48 | Claude Haiku 5.5 (Low)Anthropic | 18.6 | N/A | N/A | $0.044 | 9.5s | 1.0M | 1 | |
| 49 | K2 Horizon 375B A23BOpenInstitute of Foundation Models | 17.8 | N/A | N/A | $0.0000 | 4.9s | 524K | 1 | |
| 50 | Beam 1.0OpenReflection | 17.7 | N/A | N/A | $0.284 | 8.1s | 1.0M | 5 | |
| 51 | Nemotron 3.5 Super VLOpenNVIDIA | 13.6 | N/A | N/A | $0.556 | 6.4s | 1.0M | 7 | |
| 52 | Inkling SmallOpenThinking Machines | 12.9 | N/A | N/A | $0.203 | 14s | 524K | 2 | |
| 53 | Inkling (Xhigh)OpenThinking Machines | 12.5 | N/A | N/A | $1.35 | 14s | 1.0M | 6 | |
| 54 | Nemotron 3 Ultra 550B A55B (Reasoning)OpenNVIDIA | 11.8 | N/A | N/A | $2.23 | 19s | 262K | 4 | |
| 55 | Gemini 3.5 Flash-LiteGoogle | 11.7 | N/A | N/A | $0.693 | 7.6s | 1.0M | 1 | |
| 56 | GPT-6 Luna (Low)OpenAI | 9.7 | N/A | N/A | $0.0051 | 6.7s | 1.0M | 1 | |
| 57 | Muse Glimmer (High)OpenMeta | 6.3 | N/A | N/A | $0.161 | 23s | 131K | 3 | |
| 58 | Command A+OpenCohere | 6.2 | N/A | N/A | $0.0000 | 17s | 200K | 1 | |
| 59 | Qwen3.5 Omni PlusOpenAlibaba | 0 | N/A | N/A | N/A | 6.5s | 256K | 1 | |
| 60 | Qwen3.5 122B A10BOpenAlibaba | 0 | N/A | N/A | N/A | 5.8s | 262K | 2 | |
| 61 | Gemma 4 12BOpenGoogle | 0 | N/A | N/A | N/A | 6.3s | 262K | 1 | |
| 62 | Qwen3 Omni 30B A3B InstructOpenAlibaba | 0 | N/A | N/A | N/A | 7.1s | 66K | 1 | |
| 63 | Nova 2.0 Pro Preview (Medium)Amazon | 0 | N/A | N/A | N/A | 30s | 256K | 1 | |
| 64 | Qwen3.5 397B A17B (Reasoning)OpenAlibaba | 0 | N/A | N/A | N/A | 65s | 262K | 6 | |
| 65 | Mistral Small 4OpenMistral | 0 | N/A | N/A | N/A | 3.9s | 262K | 1 | |
| 66 | Solar Pro 4Upstage | 0 | N/A | N/A | N/A | 27s | 512K | 1 | |
| 67 | gpt-oss-20b (Low)OpenOpenAI | 0 | N/A | N/A | N/A | 11s | 131K | 3 | |
| 68 | o3OpenAI | 0 | N/A | N/A | N/A | 9.6s | 200K | 2 | |
| 69 | GLM-5.3-FlashOpenZ AI | 0 | N/A | N/A | N/A | 36s | 1.0M | 23 | |
| 70 | North Mini CodeOpenCohere | 0 | N/A | N/A | N/A | 34s | 256K | 1 | |
| 71 | Qwen3.5 9BOpenAlibaba | 0 | N/A | N/A | N/A | 7.5s | 262K | 1 | |
| 72 | Qwen3.5 122B A10B (Reasoning)OpenAlibaba | 0 | N/A | N/A | N/A | 21s | 262K | 4 | |
| 73 | NVIDIA Nemotron 3 Nano 30B A3BOpenNVIDIA | 0 | N/A | N/A | N/A | 2.5s | 262K | 3 | |
| 74 | Qwen3 Next 80B A3B InstructOpenAlibaba | 0 | N/A | N/A | N/A | 4.6s | 262K | 3 | |
| 75 | Nemotron 3.5 LightningOpenNVIDIA | 0 | N/A | N/A | N/A | 9.0s | 1.0M | 6 | |
| 76 | Phi-4 Multimodal InstructOpenMicrosoft | 0 | N/A | N/A | N/A | N/A | 4K | 1 | |
| 77 | Qwen3.5 9B (Reasoning)OpenAlibaba | 0 | N/A | N/A | N/A | 45s | 262K | 2 | |
| 78 | NVIDIA Nemotron Nano 9B V2OpenNVIDIA | 0 | N/A | N/A | N/A | 3.9s | 131K | 2 | |
| 79 | Qwen3.5 4BOpenAlibaba | 0 | N/A | N/A | N/A | 27s | 262K | 1 | |
| 80 | Qwen3.5 397B A17BOpenAlibaba | 0 | N/A | N/A | N/A | 11s | 262K | 5 | |
| 81 | Nova MicroAmazon | 0 | N/A | N/A | N/A | 2.4s | 130K | 1 | |
| 82 | Qwen3.8 27BOpenAlibaba | 0 | N/A | N/A | N/A | 15s | 1.0M | 6 | |
| 83 | gpt-oss-20b (High)OpenOpenAI | 0 | N/A | N/A | N/A | 17s | 131K | 4 | |
| 84 | Command AOpenCohere | 0 | N/A | N/A | N/A | 36s | 288K | 2 | |
| 85 | Mistral Small 4 (Reasoning)OpenMistral | 0 | N/A | N/A | N/A | 15s | 256K | 1 | |
| 86 | Sarvam 105B (High)OpenSarvam | 0 | N/A | N/A | N/A | 15s | 128K | 1 | |
| 87 | Gemma 4 E4BOpenGoogle | 0 | N/A | N/A | N/A | 11s | 131K | 1 | |
| 88 | GPT-5.3 Codex (Xhigh)OpenAI | 0 | N/A | N/A | N/A | 66s | 400K | 1 | |
| 89 | LongCat 2.0OpenLongCat | 0 | N/A | N/A | N/A | 36s | 262K | 1 | |
| 90 | Llama 3.2 Instruct 11B (Vision)OpenMeta | 0 | N/A | N/A | N/A | 18s | 131K | 1 | |
| 91 | Nova 2.0 Lite (High)Amazon | 0 | N/A | N/A | N/A | 27s | 1.0M | 1 | |
| 92 | Solar Mini 4Upstage | 0 | N/A | N/A | N/A | 23s | 524K | 1 | |
| 93 | Qwen3.5 4B (Reasoning)OpenAlibaba | 0 | N/A | N/A | N/A | 2.5 min | 262K | 1 | |
| 94 | Qwen3.8 27B (Medium)OpenAlibaba | 0 | N/A | N/A | N/A | 61s | 1.0M | 1 | |
| 95 | Qwen3.6 35B A3BOpenAlibaba | 0 | N/A | N/A | N/A | 5.3s | 262K | 7 | |
| 96 | Ministral 3 3BOpenMistral | 0 | N/A | N/A | N/A | 3.8s | 256K | 2 | |
| 97 | Gemma 4 26B A4B (Reasoning)OpenGoogle | 0 | N/A | N/A | N/A | 27s | 1.0M | 7 | |
| 98 | Qwen3.5 Omni FlashOpenAlibaba | 0 | N/A | N/A | N/A | 3.9s | 256K | 1 | |
| 99 | Nova 2.0 Lite (Low)Amazon | 0 | N/A | N/A | N/A | 24s | 1.0M | 1 | |
| 100 | Magistral Small 1.2OpenMistral | 0 | N/A | N/A | N/A | 24s | 128K | 1 | |
| 101 | Gemma 4 26B A4BOpenGoogle | 0 | N/A | N/A | N/A | 5.2s | 1.0M | 8 | |
| 102 | Ministral 3 14BOpenMistral | 0 | N/A | N/A | N/A | 8.0s | 262K | 3 | |
| 103 | Nova 2.0 LiteAmazon | 0 | N/A | N/A | N/A | 3.9s | 1.0M | 1 | |
| 104 | NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA | 0 | N/A | N/A | N/A | 10s | 262K | 4 | |
| 105 | DeepSeek V4 Flash VisionOpenDeepSeek | 0 | N/A | N/A | N/A | 15s | 1.0M | 3 | |
| 106 | Qwen3.8 27B (Low)OpenAlibaba | 0 | N/A | N/A | N/A | 61s | 1.0M | 1 | |
| 107 | Ling 3.0 TinyOpenInclusionAI | 0 | N/A | N/A | N/A | 46s | 262K | 1 | |
| 108 | Celeris-1Celeris | 0 | N/A | N/A | N/A | 0.8s | 131K | 1 | |
| 109 | Tiny Aya GlobalOpenCohere | 0 | N/A | N/A | N/A | N/A | 8K | 1 | |
| 110 | Hermes 4 - Llama-3.1 405B (Reasoning)OpenNous Research | 0 | N/A | N/A | N/A | 68s | 128K | 1 | |
| 111 | Qwen3.6 35B A3B (Reasoning)OpenAlibaba | 0 | N/A | N/A | N/A | 42s | 262K | 8 | |
| 112 | Apertus 8B InstructOpenSwiss AI Initiative | 0 | N/A | N/A | N/A | 6.3s | 64K | 1 | |
| 113 | Nemotron 3 Nano Omni 30B A3B ReasoningOpenNVIDIA | 0 | N/A | N/A | N/A | 12s | 262K | 2 | |
| 114 | Kimi K2.7 CodeOpenKimi | 0 | N/A | N/A | N/A | 50s | 262K | 6 | |
| 115 | Qwen3.8 2.4T A95BOpenAlibaba | 0 | N/A | N/A | N/A | 63s | 1.0M | 6 | |
| 116 | Llama 4 MaverickOpenMeta | 0 | N/A | N/A | N/A | 11s | 1.0M | 5 | |
| 117 | Ministral 3 8BOpenMistral | 0 | N/A | N/A | N/A | 6.6s | 262K | 2 | |
| 118 | Llama 3.3 Instruct 70BOpenMeta | 0 | N/A | N/A | N/A | 7.4s | 131K | 8 | |
| 119 | Qwen3.8-Flash-NextOpenAlibaba | 0 | N/A | N/A | N/A | 47s | 1.0M | 1 | |
| 120 | Phi-4 Mini InstructOpenMicrosoft | 0 | N/A | N/A | N/A | 12s | 128K | 1 |
2Claude Opus 5.5Anthropicintelligence58.4Task $0.976Response 10s1.0M context4 providers
3GPT-6 AstraOpenAIintelligence56.9Task $6.24Response 4.5 min1.0M context4 providers
4GPT-6 Astra (Xhigh)OpenAIintelligence55.3Task $3.66Response 2.2 min1.0M context1 provider
5GPT-6 Astra (High)OpenAIintelligence54.8Task $3.24Response 41s1.0M context1 provider
6GPT-6.1 SolOpenAIintelligence54.5Task $1.27Response 4.3 min1.0M context5 providers
7Claude Sonnet 5.5Anthropicintelligence54.2Task $0.511Response 5.8s1.0M context4 providers
8GPT-6.1 Sol (Xhigh)OpenAIintelligence52.3Task $0.764Response 1.7 min1.0M context1 provider
9GPT-6 Astra (Medium)OpenAIintelligence51.5Task $2.73Response 11s1.0M context1 provider
10GPT-6.1 TerraOpenAIintelligence51Task $0.226Response 6.5s1.0M context1 provider
11Gemini 4 Argon (High)Googleintelligence50.4Task $7.68Response 53s1.0M context2 providers
12GPT-6.1 Sol (High)OpenAIintelligence50.2Task $0.591Response 38s1.0M context1 provider
13Claude Fable 5.1Anthropicintelligence49.7Task $4.47Response 10s1.0M context1 provider
14GPT-6.1 Sol (Medium)OpenAIintelligence46.1Task $0.359Response 12s1.0M context1 provider
15Kimi K3.1 ProOpenKimiintelligence46Task $3.68Response 73s1.0M context2 providers
16GPT-6.1 Terra (Xhigh)OpenAIintelligence45Task $0.401Response 32s1.0M context1 provider
17Muse WonderOpenMetaintelligence43.3Task $6.95Response 36s1.0M context1 provider
18GPT-6 Astra (Low)OpenAIintelligence43Task $1.42Response 11s1.0M context2 providers
19GPT-6.1 Terra (High)OpenAIintelligence42.3Task $0.259Response 12s1.0M context1 provider
20GPT-6.1 Terra (Medium)OpenAIintelligence38.1Task $0.169Response 7.6s1.0M context1 provider
21Claude Haiku 5.5Anthropicintelligence36.2Task $0.411Response 5.7 min1.0M context1 provider
22Grok 4.7 (High)SpaceXAIintelligence35Task $6.18Response 24s500K context1 provider
23GPT-6.1 Sol (Low)OpenAIintelligence34.5Task $0.162Response 11s1.0M context1 provider
24Claude Haiku 5.5 (Xhigh)Anthropicintelligence34.3Task $0.248Response 66s1.0M context1 provider
25Grok 4.7 (Xhigh)SpaceXAIintelligence34.3Task $7.51Response 35s500K context1 provider
26Qwen3.8 MaxOpenAlibabaintelligence33.6Task $10Response 64s984K context1 provider
27DeepSeek V4.1 Flash 1017OpenDeepSeekintelligence32.5Task $0.602Response 15s1.0M context21 providers
28GLM-5.3OpenZ AIintelligence31.7Task $5.01Response 36s1.0M context26 providers
29Grok 4.7 (Low)SpaceXAIintelligence30.9Task $2.92Response 13s500K context1 provider
30Gemini 3.8 Flash (High)Googleintelligence30.5Task $7.77Response 29s1.0M context1 provider
Showing 120 of 147 models.
Reading the field
How to use this LLM ranking page
Start with capability, then force the economics
Frontier models often cluster tightly on raw intelligence. Cost per task, response time, provider coverage, and context length usually create the real shortlist.
Move from discovery to a defensible final pick
Use Explore to find the shape of the market, then move into Compare or use the Agentic Fit Finder when task-level reliability and cost matter more than chat quality alone.
Field notes
Questions builders ask
What is the best LLM in 2026?
Gemini 4 Carbon (High) leads the overall quality ranking right now. The best model for you depends on your use case — coding, cost, speed, and context length all shift the answer.
How do I compare LLMs?
Sort by Quality Index for overall strength, then filter by price, speed, or context window to match your constraints. Move to the Compare page to put 2–4 finalists head to head.
Which AI model has the best quality-to-price ratio?
Open-weight models like DeepSeek, Qwen, and Llama often lead on quality-to-price. For agentic workflows, cost per task is usually a better filter than token price alone.
How often is this leaderboard updated?
Data is pulled from Artificial Analysis and refreshed automatically. New models appear as soon as they have benchmark scores and provider endpoints.
Ranking library
Current live rankings
Focused rankings for the decisions engineers actually make.
01CodingBest LLM for CodingLiveCodeBench, Terminal-Bench, SciCode, and engineering fit.Open ranking 02OpenBest Open Source LLMOpen-weight models for self-hosting and lower-cost deployment.Open ranking 03LocalBest Local LLMModels mapped to Mac, RTX, workstation, and server hardware.Open ranking 04Local codingBest Local LLM for CodingCoding strength filtered through realistic hardware limits.Open ranking 05OllamaBest Ollama ModelsLow-friction local models for coding, reasoning, and chat.Open ranking 06ContextLargest Context Window LLMLong documents, codebases, and retrieval-heavy work.Open ranking 07AgentsBest Agentic ModelsTool use, multi-step execution, and autonomous workflows.Open ranking