1
GPT-5.6 Sol
- Vendor
- OpenAI
- Score
- 57.2
- Context
- 1.1M
- Pricing (in/out per 1M)
- $7.78

Composite ranking of AI LLMs as of 2026-08-07, synthesized from llm-stats.com, Vellum, and LMArena. Includes score, pricing, and context window.
Ranking methodology has not been provided.
References: 0. Page edits do not imply that the underlying data is newer.
As of 2026-08-07, GPT-5.6 Sol leads the composite score, with Anthropic Claude Opus 5 / Fable 5 / Mythos Preview filling the top four. Kimi K3, GPT-5.6 Terra, and Qwen3.8 Max form the second tier. Ranks 1-15 are ordered by llm-stats composite score; 16-20 are supplemented with LMArena ELO and Vellum category scores.
| Rank | Model |
|---|
No sign-in required. Feedback is reviewed before any content is changed. Limit: 5 per day.
| Vendor |
|---|
| Score |
|---|
| Context |
|---|
| Pricing (in/out per 1M) |
|---|
| 1 | GPT-5.6 Sol | OpenAI | 57.2 | 1.1M | $7.78 |
| 2 | Claude Opus 5 | Anthropic | 56.5 | 1M | $5 / $25 |
| 3 | Claude Fable 5 | Anthropic | 56.3 | 1M | $10 / $50 |
| 4 | Claude Mythos Preview | Anthropic | 56 | — | — |
| 5 | Kimi K3 | Moonshot AI | 55.4 | 1M | $4.33 |
| 6 | GPT-5.6 Terra | OpenAI | 52.7 | 1.1M | $3.11 |
| 7 | Qwen3.8 Max | Alibaba (Qwen) | 52.5 | — | — |
| 8 | Claude Opus 4.8 | Anthropic | 52.3 | 1M | $7.22 |
| 9 | Muse Spark 1.1 | Meta | 51.6 | 1M | $1.58 |
| 10 | Claude Sonnet 5 | Anthropic | 50.1 | 1M | $2.89 |
| 11 | GPT-5.5 | OpenAI | 49.4 | 1.1M | $7.78 |
| 12 | Grok 4.5 | xAI | 48.6 | 500K | $2.44 |
| 13 | DeepSeek-V4-Flash-0731 | DeepSeek | 48.3 | 1M | $0.10 |
| 14 | Seed 2.1 Pro | ByteDance | 47.2 | — | — |
| 15 | GLM-5.2 | Zhipu AI | 46.8 | 1M | $1.18 |
Comments