CL-bench Life leaderboard
As of 6 Nov 2026, the top score on CL-bench Life is 22.2% by GPT-5.5 (OpenAI), ahead of GPT-5.4 at 21.7%, across 16 model configurations with a published result (Epoch AI Benchmarking Hub, result dated 23 Apr 2026). CL-bench tasks drawn from everyday situations. CL-bench Life is shown for reference only and does not count toward the BenchLeader Index.
Key facts (as of 6 Nov 2026)
- GPT-5.5 holds the top CL-bench Life score at 22.2% (Epoch AI Benchmarking Hub, 23 Apr 2026).
- GPT-5.4 is second on CL-bench Life at 21.7% (Epoch AI Benchmarking Hub, 5 Mar 2026).
- CL-bench Life: The everyday-life subset of CL-bench (Epoch AI Benchmarking Hub).
- 16 model configurations have a published CL-bench Life result on BenchLeader (BenchLeader, 6 Nov 2026).
- CL-bench Life does not feed the BenchLeader Index; it is shown for reference (BenchLeader methodology).
The everyday-life subset of CL-bench.
- Published by
- Epoch AI Benchmarking Hub
- Category
- Reasoning
- Index weight
- Reference only
- Models
- 16
- Data as of
- 6 Nov 2026
CC BY 4.0 — Epoch AI, ‘AI Benchmarking Hub’, epoch.ai/benchmarks. Mirrored boards credit their original publishers.
What the test looks like
CL-bench tasks drawn from everyday situations.
How it is scored
Overall score, as published.
What to keep in mind
New; small set.
- 1GPT-5.5 (high)22.2%
- 2GPT-5.4 (xhigh)21.7%
- 3GPT-5.4 (high)19.3%
- 4GPT-5.1 (high)17.3%
- 5Claude Opus 4.6 (high)17.0%
- 6Gemini 3.1 Pro16.9%
- 7GPT-5.413.8%
- 8Claude Opus 4.613.6%
- 9DeepSeek V4 Pro (high)13.5%
- 10Kimi K2.513.2%
- 11Qwen3.5 Plus12.4%
- 12Grok 4.2011.9%
- 13GLM 4.710.9%
- 14DeepSeek V3.2 (thinking)9.5%
- 15Mimo v2 Pro6.9%
| # | ||||
|---|---|---|---|---|
| 1 |  GPT-5.5high | 22.2% | 63.7 | 2026-04-23 |
| 2 | GPT-5.4xhigh | 21.7% | 63.2 | 2026-03-05 |
| 3 | GPT-5.4high | 19.3% | 58.8 | 2026-03-05 |
| 4 | GPT-5.1high | 17.3% | 57.7 | 2025-11-13 |
| 5 |  Claude Opus 4.6high | 17.0% | 62.6 | 2026-02-05 |
| 6 |  Gemini 3.1 Pro | 16.9% | 60.5 | 2026-02-19 |
| 7 | GPT-5.4 | 13.8% | 58.0 | 2026-03-05 |
| 8 | Claude Opus 4.6 | 13.6% | 62.3 | 2026-02-05 |
| 9 |  DeepSeek V4 Prohighopen ↗ | 13.5% | 57.5 | 2026-04-24 |
| 10 |  Kimi K2.5open ↗ | 13.2% | 54.2 | 2026-01-27 |
| 11 |  Qwen3.5 Plus | 12.4% | – | 2026-02-16 |
| 12 |  Grok 4.20 | 11.9% | – | 2026-02-17 |
| 13 |  GLM 4.7open ↗ | 10.9% | 51.7 | 2025-12-22 |
| 14 | DeepSeek V3.2thinkingopen ↗ | 9.5% | 56.6 | 2025-09-29 |
| 15 |  Mimo v2 Pro | 6.9% | 59.1 | – |
| 16 |  MiniMax M2.5open ↗ | 6.3% | 53.6 | 2026-02-12 |
More reasoning benchmarks · All LLM benchmarks
Related benchmarks
Top head-to-heads on CL-bench Life
Cite as: BenchLeader, “CL-bench Life leaderboard”, data as of 6 Nov 2026, https://www.benchleader.com/benchmarks/cl_bench_life.
CL-bench Life: questions
- What does CL-bench Life measure?
- CL-bench tasks drawn from everyday situations. Scores are reported in percent of tasks solved; higher is better.
- What is the top score on CL-bench Life?
- As of 6 Nov 2026, the highest score on CL-bench Life is 22.2% by GPT-5.5 (result dated 23 Apr 2026), ahead of GPT-5.4 at 21.7%. Scores come from Epoch AI Benchmarking Hub and are re-read daily.
- Which AI model leads CL-bench Life?
- GPT-5.5 leads CL-bench Life with 22.2% as of 6 Nov 2026 (result dated 23 Apr 2026), ahead of GPT-5.4 at 21.7%.
- How many models have CL-bench Life results?
- 16 model configurations have a CL-bench Life result on BenchLeader, all taken from Epoch AI Benchmarking Hub.
- Who runs CL-bench Life and how often is it updated?
- CL-bench Life is published by Epoch AI Benchmarking Hub. BenchLeader re-reads the published results once a day and records the date each result was published.
- Does CL-bench Life count toward the BenchLeader Index?
- No. CL-bench Life is shown for reference but left out of the composite index.