Reasoning benchmark
Bench to the Future 3 leaderboard
As of October 2026, GLM-5.3 has the highest published Bench to the Future 3 score on Noometry at 0.15, out of 10 models with results.
Last verified
About Bench to the Future 3
A description with primary sources is being prepared for this benchmark.
Top 10 models
- GLM-5.3 0.15
- GLM-5.3-Flash 0.15
- GPT-5.5 0.14
- Claude Sonnet 5 0.14
- Muse Spark 1.3 0.14
- Claude Opus 4.8 0.14
- GPT-5.6 Sol 0.14
- GPT-6 Astra 0.14
- Claude Fable 5 0.13
- Claude Opus 5 0.12
Sponsored placements are available on pages like this one. Advertise on Noometry
All results
| # | Model | Provider | Rating | Setting | Source | Date |
|---|---|---|---|---|---|---|
| 1 | GLM-5.3 | Z.ai (Zhipu) | 0.15 | Epoch AI | ||
| 2 | GLM-5.3-Flash | Z.ai (Zhipu) | 0.15 | Epoch AI | ||
| 3 | GPT-5.5 | OpenAI | 0.14 | high | Epoch AI | |
| 4 | Claude Sonnet 5 | Anthropic | 0.14 | xhigh | Epoch AI | |
| 5 | Muse Spark 1.3 |  Meta | 0.14 | xhigh | Epoch AI | |
| 6 | Claude Opus 4.8 | Anthropic | 0.14 | high | Epoch AI | |
| 7 | GPT-5.6 Sol | OpenAI | 0.14 | max | Epoch AI | |
| 8 | GPT-6 Astra | OpenAI | 0.14 | low | Epoch AI | |
| 9 | Claude Fable 5 | Anthropic | 0.13 | high | Epoch AI | |
| 10 | Claude Opus 5 | Anthropic | 0.12 | xhigh | Epoch AI |
Compare the leaders
Frequently asked questions
Which model has the highest Bench to the Future 3 score?
As of October 2026, GLM-5.3 has the highest published Bench to the Future 3 score on Noometry at 0.15, out of 10 models with results.
What is the best open-weight model on Bench to the Future 3?
GLM-5.3 has the highest Bench to the Future 3 score among open-weight models at 0.15, ranking 1 of 10 overall.