1
Anthropic
AnthropicClaude Opus 5.5
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
OpenAI
OpenAIGPT-6 Astra
97/100
Overall
3Anthropic
AnthropicClaude Fable 5.1
96/100
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.
- GPT-6 Astra99
- Claude Opus 5.598
- Claude Fable 5.196
- Claude Fable 595
- Claude Sonnet 5.595
Software Engineering
Code generation, debugging and algorithmic thinking under real constraints.
- Claude Opus 5.599
- Claude Sonnet 5.599
- GPT-6 Astra98
- Claude Fable 5.197
- Claude Opus 595
Conversational Intelligence
Reading intent, tone and nuance across natural language exchanges.
- Gemini 4 Argon99
- Claude Opus 5.597
- Claude Fable 596
- Claude Fable 5.196
- Claude Opus 595
— 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 Opus 5.5 Anthropic | 98 | 99 | 97 | 98 |
| 2 | GPT-6 Astra OpenAI | 99 | 98 | 93 | 97 |
| 3 | Claude Fable 5.1 Anthropic | 96 | 97 | 96 | 96 |
| 4 | Claude Sonnet 5.5 Anthropic | 95 | 99 | 93 | 96 |
| 5 |  Claude Fable 5 Anthropic | 95 | 94 | 96 | 95 |
| 6 |  Gemini 4 Argon Google | 95 | 92 | 99 | 95 |
| 7 |  Claude Opus 5 Anthropic | 93 | 95 | 95 | 94 |
| 8 | GPT-6.1 Sol OpenAI | 95 | 94 | 91 | 93 |
| 9 |  Muse Spark 1.3 Meta | 92 | 92 | 95 | 93 |
| 10 |  GPT-5.6 Sol OpenAI | 92 | 93 | 90 | 92 |
| 11 | GPT-6 Sol OpenAI | 93 | 93 | 90 | 92 |
| 12 |  Qwen3.8 Max Alibaba (Qwen) | 91 | 92 | 89 | 91 |
| 13 |  Kimi K3 Moonshot AI | 89 | 91 | 90 | 90 |
| 14 | Gemini 3.8 Flash Google | 88 | 86 | 92 | 89 |
| 15 |  Grok 4.7 xAI (SpaceXAI) | 91 | 90 | 87 | 89 |
| 16 |  MiMo-V2.6-Pro Xiaomi | 90 | 89 | 88 | 89 |
| 17 |  Claude Opus 4.8 Anthropic | 88 | 88 | 89 | 88 |
| 18 |  GLM-5.3 Z.ai | 88 | 88 | 87 | 88 |
| 19 |  Grok 4.6 xAI (SpaceXAI) | 87 | 88 | 85 | 87 |
| 20 |  Claude Sonnet 5 Anthropic | 84 | 86 | 87 | 86 |
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.