1
Anthropic
AnthropicClaude Fable 5
98/100
Overall
— LLM Leaderboard —
Ranked by the people
who use them.
Community-driven rankings of the leading large language models, scored by accredited AI practitioners across the capabilities that matter in real work: reasoning, engineering and conversation. No vendor benchmarks, no marketing claims. Just the verdict of the people who build with them every day.
— Overall standings —
The models out
in front.
2
Anthropic
AnthropicClaude Opus 5
96/100
Overall
3
OpenAI
OpenAIGPT-5.6 Sol
94/100
Overall
— Capability by capability —
Where each model
actually wins.
The top five performers in every category, scored on the work practitioners do most.
Professional Reasoning
Complex problem-solving and analytical judgement in real-world scenarios.
- Claude Fable 598
- Claude Opus 596
- GPT-5.6 Sol94
- Grok 4.693
- Claude Opus 4.891
Software Engineering
Code generation, debugging and algorithmic thinking under real constraints.
- Claude Fable 599
- Claude Opus 596
- GPT-5.6 Sol96
- Kimi K394
- Grok 4.693
Conversational Intelligence
Reading intent, tone and nuance across natural language exchanges.
- Claude Opus 597
- Claude Fable 596
- Claude Opus 4.894
- Gemini 3.1 Pro92
- GPT-5.6 Sol92
— Top ranked —
The top-rated
models.
The highest-rated models, side by side. Tap any score column to re-rank the board by that capability.
| # | Model | ||||
|---|---|---|---|---|---|
| 1 | Claude Fable 5 Anthropic | 98 | 99 | 96 | 98 |
| 2 | Claude Opus 5 Anthropic | 96 | 96 | 97 | 96 |
| 3 | GPT-5.6 Sol OpenAI | 94 | 96 | 92 | 94 |
| 4 |  Claude Opus 4.8 Anthropic | 91 | 92 | 94 | 92 |
| 5 |  Grok 4.6 xAI | 93 | 93 | 89 | 92 |
| 6 |  Kimi K3 Moonshot AI | 91 | 94 | 89 | 91 |
| 7 |  Gemini 3.1 Pro Google | 89 | 85 | 92 | 89 |
| 8 |  Claude Sonnet 5 Anthropic | 87 | 88 | 90 | 88 |
| 9 |  Qwen3.8 Max Qwen | 88 | 87 | 85 | 87 |
| 10 |  GPT-5.6 Terra OpenAI | 86 | 86 | 87 | 86 |
| 11 |  GPT-5.5 OpenAI | 85 | 84 | 86 | 85 |
| 12 |  Grok 4.5 xAI | 85 | 84 | 85 | 85 |
| 13 |  Claude Opus 4.7 Anthropic | 84 | 84 | 84 | 84 |
| 14 |  Muse Spark 1.2 Meta | 84 | 83 | 85 | 84 |
| 15 |  DeepSeek V4 Pro DeepSeek | 83 | 85 | 80 | 83 |
| 16 |  Gemini 3.7 Flash Google | 82 | 84 | 84 | 83 |
| 17 |  GLM-5.2 Z.ai | 81 | 82 | 79 | 81 |
| 18 |  Gemini 3.6 Flash Google | 79 | 80 | 82 | 80 |
| 19 |  GPT-5.6 Luna OpenAI | 77 | 77 | 82 | 79 |
| 20 |  DeepSeek V4 Flash DeepSeek | 78 | 80 | 77 | 78 |
Help shape the rankings
Scored by the people
who build with AI.
Our leaderboard is ranked by accredited practitioners. Join the Institute to lend your expertise to the standard.