llm.ing

Every LLM benchmark, one honest table.

Scores, prices, and speed for 185 models — aggregated from public sources, with the origin and provenance of every number visible. Refreshed automatically, last 5h ago.

Frontier right now

Full leaderboard →
#ModelLabContext$/1M in · outIntelligenceCodingAgenticArena Elo
1Claude Fable 5.2Anthropic1M$8 · $4064.6———
2GPT-6.2 AstraOpenAI1.1M$8 · $4062.1———
3Gemini 4 NeonGoogle1.0M$3 · $1561.4———
4Gemini 4 CarbonGoogle1.0M$2 · $1060.0———
5Claude Opus 5.5Anthropic1M$4 · $2059.1——1516
6GPT-6.2 SolOpenAI1.1M$2 · $1057.3———
7GPT-6 AstraOpenAI1.1M$10 · $5056.976.951.0—
8GPT-6.1 SolOpenAI1.1M$2 · $1054.6———
9Claude Sonnet 5.5Anthropic1M$2 · $1054.5——1470
10Gemini 4 HydrogenGoogle1.0M$1.5 · $7.553.9———
11GPT-6.1 TerraOpenAI1.1M$1 · $551.3———
12Gemini 4 ArgonGoogle1.0M$2 · $1050.4——1533
13Claude Fable 5.1Anthropic1M$10 · $5050.081.657.9—
14Claude Opus 5Anthropic1M$5 · $2549.778.056.51502
15Claude Fable 5Anthropic1M$10 · $5049.676.550.71493

Intelligence, coding & agentic indices by Artificial Analysis; Arena Elo by LMArena (CC BY 4.0). Best value across model variants shown.

Intelligence vs. price

The frontier you actually pay for — up and to the left is better. Hover a point for details; click it to open the model. Free-tier models excluded.

API-onlyOpen weights
51015202530354045505560↑ AA Intelligence Index$0.1$0.2$1$2$10$20$100input price, $ per 1M tokens →DeepSeek R1 $0.571/1M in · index 13.1DeepSeek V3.2 $0.26/1M in · index 21.5DeepSeek V4 Flash $0.15/1M in · index 34.3DeepSeek V4 Pro $0.66/1M in · index 23.1Claude Sonnet 4.6 $3/1M in · index 30.1Claude Haiku 4.5 (latest) $1/1M in · index 7.4Claude Opus 4.6 $5/1M in · index 31.9Claude Fable 5 $10/1M in · index 49.6Claude Opus 4.8 $5/1M in · index 41.8Claude Opus 4.1 (latest) $15/1M in · index 22.8Claude Sonnet 4.5 (latest) $3/1M in · index 20.7Claude Opus 4.7 $5/1M in · index 40.7Claude Opus 4.5 (latest) $5/1M in · index 29.1Claude Sonnet 5 $2/1M in · index 38.2GPT-5.1 Codex mini $0.25/1M in · index 20.4GPT-4.1 mini $0.4/1M in · index 10.2GPT-4o $2.5/1M in · index 8.4GPT-5.6 Sol $4/1M in · index 47.0GPT-4.1 nano $0.1/1M in · index 7.8o3-mini $1.1/1M in · index 12.5GPT-5.5 $5/1M in · index 38.4o3-pro $20/1M in · index 21.9GPT-4o mini $0.15/1M in · index 6.7GPT-5 $1.25/1M in · index 23.0GPT-3.5-turbo $0.5/1M in · index 5.5GPT-5.4 $2.5/1M in · index 39.0GPT-5.2 Codex $1.75/1M in · index 28.5GPT-5.4 nano $0.2/1M in · index 20.7GPT-5.4 mini $0.75/1M in · index 24.1o1 $15/1M in · index 15.2GPT-5.6 Luna $0.2/1M in · index 23.8GPT-5.2 $1.75/1M in · index 30.4GPT-5.3 Codex $1.75/1M in · index 32.5GPT-5 Mini $0.25/1M in · index 20.6o1-pro $150/1M in · index 12.4GPT-5.1 $1.25/1M in · index 37.5GPT-4 Turbo $10/1M in · index 7.0GPT-5.1 Codex $1.25/1M in · index 23.7GPT-5 Nano $0.05/1M in · index 13.0o3 $2/1M in · index 20.2GPT-5.6 Terra $2/1M in · index 32.3GPT-4.1 $2/1M in · index 12.7o4-mini $1.1/1M in · index 16.7GPT-4 $30/1M in · index 6.7Gemini 3.5 Flash $1.5/1M in · index 33.6Gemini 2.5 Flash $0.3/1M in · index 15.5Gemini 3.5 Flash Lite $0.3/1M in · index 11.7Gemini 3.1 Flash Lite Preview $0.25/1M in · index 6.2Gemini 3 Flash Preview $0.5/1M in · index 26.3Gemini 3.6 Flash $0.75/1M in · index 34.0Gemini 3.1 Pro Preview $2/1M in · index 29.7Gemini 2.5 Pro $1.25/1M in · index 16.1Gemini 2.5 Flash-Lite $0.1/1M in · index 10.4Grok 4.3 $1.25/1M in · index 24.9Grok 4.20 (Non-Reasoning) $1.25/1M in · index 25.7Grok 4.5 $2/1M in · index 38.8Grok Build 0.1 $1/1M in · index 27.2Muse Spark 1.1 $1.25/1M in · index 33.7Devstral 2 $0.4/1M in · index 8.6Magistral Small $0.5/1M in · index 8.2Qwen3-Coder 480B-A35B Instruct $1.5/1M in · index 11.9Qwen3.7 Plus $0.4/1M in · index 25.2Qwen3 32B $0.7/1M in · index 7.3Qwen3.6 35B-A3B $0.375/1M in · index 18.2Qwen3-Coder 30B-A3B Instruct $0.45/1M in · index 9.6Qwen3.5 27B $0.3/1M in · index 30.0Qwen3-VL 235B-A22B $0.7/1M in · index 13.4Qwen3.7 Max $2.5/1M in · index 29.5Qwen3-Next 80B-A3B (Thinking) $0.5/1M in · index 11.2Qwen3.6 27B $0.6/1M in · index 21.4Qwen3.5 35B-A3B $0.25/1M in · index 19.3Qwen3-VL 30B-A3B $0.2/1M in · index 9.5Qwen3 14B $0.35/1M in · index 6.7Qwen2.5 32B Instruct $0.7/1M in · index 6.9Qwen3 235B-A22B $0.7/1M in · index 12.7Qwen3 Max $1.2/1M in · index 21.3Qwen3 8B $0.18/1M in · index 7.3Qwen Turbo $0.05/1M in · index 6.4Qwen3.5 397B-A17B $0.6/1M in · index 21.4Qwen3.6 Max Preview $1.3/1M in · index 28.4Qwen3.6 Plus $0.5/1M in · index 27.0Qwen3.5 122B-A10B $0.4/1M in · index 17.7Qwen3-Next 80B-A3B Instruct $0.5/1M in · index 9.6Kimi K2.5 $0.6/1M in · index 23.5Kimi K2.6 $0.95/1M in · index 27.0Kimi K2.7 Code $0.95/1M in · index 25.8Kimi K2 Thinking $0.6/1M in · index 22.0Kimi K3 $3/1M in · index 17.4GLM-5 $0.598/1M in · index 27.9GLM-5.1 $0.896/1M in · index 26.1GLM-5.2 $1.2/1M in · index 33.7GLM-5V-Turbo $0.747/1M in · index 23.5GLM-4.7 $0.448/1M in · index 22.2GLM-4.5V $0.299/1M in · index 7.6GLM-4.5 $0.6/1M in · index 12.8GLM-4.6 $0.6/1M in · index 18.5GLM-4.5-Air $0.12/1M in · index 11.1GLM-4.6V $0.149/1M in · index 11.2MiniMax-M2 $0.3/1M in · index 18.6MiniMax-M2.7 $0.3/1M in · index 38.9MiniMax-M2.1 $0.3/1M in · index 20.9MiniMax-M2.5 $0.3/1M in · index 22.8MiniMax-M3 $0.3/1M in · index 18.9Nemotron 3 Super $0.2/1M in · index 12.8Sonar $1/1M in · index 8.7Sonar Pro $3/1M in · index 7.6Sonar Reasoning Pro $2/1M in · index 11.8Mercury 2 $0.25/1M in · index 10.8Step 3.7 Flash $0.202/1M in · index 19.5Claude Opus 5 $5/1M in · index 49.7Qwen3.8 Max $2/1M in · index 33.7Muse Spark 1.2 $1.25/1M in · index 39.6Grok 4.6 $2/1M in · index 31.0Gemini 3.7 Flash $0.75/1M in · index 39.6DeepSeek V4 Flash Vision Exp $0.15/1M in · index 34.8GLM-5.3 $1.2/1M in · index 31.7GLM-5.3-Flash $0.12/1M in · index 27.8Qwen3.8 Flash $0.15/1M in · index 28.6Claude Fable 5.1 $10/1M in · index 50.0Gemini 3.8 Flash $0.75/1M in · index 30.8Muse Spark 1.3 $1.25/1M in · index 36.6GPT-6 Astra $10/1M in · index 56.9Mercury 2.5 $0.2/1M in · index 12.3Grok 4.7 $2/1M in · index 35.5Claude Opus 5.5 $4/1M in · index 59.1GPT-6 Luna $0.1/1M in · index 27.9GPT-6 Sol $2/1M in · index 44.2Step 5 Preview $1.05/1M in · index 28.5Claude Sonnet 5.5 $2/1M in · index 54.5GPT-6.1 Sol $2/1M in · index 54.6Mistral Large 4 $0.7/1M in · index 25.3Ministral 3 8B $0.15/1M in · index 5.5Ministral 3 14B $0.2/1M in · index 6.0Ministral 3 3B $0.1/1M in · index 4.8Claude Haiku 5.5 $0.1/1M in · index 36.5Gemini 4 Argon $2/1M in · index 50.4MiniMax-M3.1-Flash $0.15/1M in · index 29.1Kimi K3.1 Pro $2/1M in · index 46.5GPT-6.1 Terra $1/1M in · index 51.3Claude Fable 5.2 $8/1M in · index 64.6Gemini 4 Carbon $2/1M in · index 60.0Gemini 4 Hydrogen $1.5/1M in · index 53.9Qwen3.8 27B $0.08/1M in · index 20.1GPT-6.2 Astra $8/1M in · index 62.1GPT-6.2 Sol $2/1M in · index 57.3Gemini 4 Neon $3/1M in · index 61.4Claude Fable 5.2GPT-6.2 AstraGemini 4 NeonGemini 4 CarbonClaude Opus 5.5GPT-6.2 Sol

New models

How to read the numbers

  • independent — measured by an independent evaluator
  • crowd — human preference votes (Elo)
  • mirror — mirrored via an aggregator API
  • vendor — self-reported by the model's vendor

Every score keeps a link to where it came from and when we saw it. Read the methodology.