LLM Leaderboard
Ranked by Intelligence Index · source AA
Artificial Analysis composite of reasoning, knowledge, coding, math.
#1 by Intelligence Index
Gemini 4 Carbon (High)
60.0
Google · in $4.00 / out $20.0 per 1M · 89 tok/s
| # | Model | Intelligence |
|---|---|---|
| 1 | Gemini 4 Carbon (High) | 60.0 |
| 2 | Claude Opus 5.5 (Max, Default Fallback) | 59.1 |
| 3 | Gemini 4 Carbon (Medium) | 58.3 |
| 4 | Claude Opus 5.5 (Xhigh, Default Fallback) | 57.4 |
| 5 | GPT-6 Astra (Max) | 56.9 |
| 6 | GPT-6 Astra (Xhigh) | 55.3 |
| 7 | GPT-6 Astra (High) | 54.8 |
| 8 | GPT-6.1 Sol (Max) | 54.6 |
| 9 | Claude Sonnet 5.5 (Max, Default Fallback) | 54.5 |
| 10 | Gemini 4 Carbon (Low) | 54.2 |
| 11 | Muse Spark 1.3 (max) | 53.0 |
| 12 | GPT-6.1 Sol (Xhigh) | 52.5 |
| 13 | Claude Opus 5.5 (High, Default Fallback) | 51.8 |
| 14 | GPT-6 Astra (Medium) | 51.6 |
| 15 | GPT-6.1 Terra (Max) | 51.3 |
| 16 | Gemini 4 Argon (High) | 50.4 |
| 17 | GPT-6.1 Sol (High) | 50.3 |
| 18 | Muse Wonder Full (Max) | 50.1 |
| 19 | Claude Fable 5.1 (Xhigh, Default Fallback) | 50.0 |
| 20 | Claude Sonnet 5.5 (Xhigh, Default Fallback) | 49.9 |
| 21 | Claude Fable 5.1 (Max, Default Fallback) | 49.2 |
| 22 | Claude Opus 5.5 (Medium, Default Fallback) | 48.2 |
| 23 | Claude Fable 5.1 (High, Default Fallback) | 47.2 |
| 24 | Kimi K3.1 Pro | 46.5 |
| 25 | GPT-6.1 Sol (Medium) | 46.3 |
| 26 | GPT-6.1 Terra (Xhigh) | 45.3 |
| 27 | GPT-6 Astra (Non-reasoning) | 45.2 |
| 28 | GPT-6 Sol (Max) | 44.2 |
| 29 | Muse Wonder (Max) | 43.6 |
| 30 | GPT-6 Astra (Low) | 43.3 |
| 31 | Claude Fable 5.1 (Medium, Default Fallback) | 43.2 |
| 32 | GPT-6.1 Terra (High) | 42.4 |
| 33 | Claude Sonnet 5.5 (High, Default Fallback) | 41.5 |
| 34 | Claude Fable 5.1 (Low, Default Fallback) | 38.7 |
| 35 | GPT-6.1 Terra (Medium) | 38.2 |
| 36 | Muse Spark 1.3 (Max) | 36.6 |
| 37 | Claude Haiku 5.5 (Max) | 36.5 |
| 38 | Agnes 3.0 Flash | 35.5 |
| 39 | Grok 4.7 (Xhigh) | 35.5 |
| 40 | Grok 4.7 (High) | 35.2 |
| 41 | GPT-6.1 Sol (Low) | 34.8 |
| 42 | Claude Opus 5.5 (Low, Default Fallback) | 34.8 |
| 43 | Claude Haiku 5.5 (Xhigh) | 34.6 |
| 44 | Qwen3.8 Max (0902) | 33.7 |
| 45 | DeepSeek V4.1 Flash 1017 (Max) | 32.6 |
| 46 | GPT-5.6 Terra (Max) | 32.3 |
| 47 | GLM-5.3 (Max) | 31.7 |
| 48 | G9v3-39A5B | 31.6 |
| 49 | Grok 4.7 (Low) | 31.1 |
| 50 | Claude Sonnet 5.5 (Medium, Default Fallback) | 30.8 |
Quality, pricing, and speed benchmarks via Artificial Analysis. Human preference Elo via LMArena. Refreshed daily at 06:00 UTC · last sync .
About the metrics
Intelligence Index
AA
Artificial Analysis composite of reasoning, knowledge, coding, math.
LMArena Elo
LMArena
Human preference Elo from chatbot arena head-to-head votes.
Coding Index
AA
AA composite — LiveCodeBench, SciCode, etc.
Math Index
AA
AA composite — MATH-500, AIME, etc.
MMLU-Pro
AA
Multi-domain knowledge & reasoning. Harder than MMLU.
GPQA Diamond
AA
Graduate-level science Q&A. Strong reasoning signal.
LiveCodeBench
AA
Competitive programming, contamination-resistant.
MATH-500
AA
Subset of the MATH benchmark.
AIME
AA
American Invitational Mathematics Examination — olympiad math.
Humanity's Last Exam
AA
Frontier reasoning benchmark; most models still score low.
SciCode
AA
Scientific coding tasks.