AIME 2025
Harbor adapterAIME 2025: 30道AIME级数学题
Verified86%Math
- Samples
- 30
- Released
- 2025
- Scores
- 12
CL-bench Life
CL-bench Life: Can Language Models Learn from Real-Life Context?
How to run
ltb · cl-bench-life
$ npm i -g lettokenburn-cli$ ltb bench info cl-bench-life
External harness. No Harbor adapter has been generated for this benchmark yet. `ltb bench info` prints the known links.
Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs
Scores
14 sourced entries| Harness | Source | Confidence | Link | |||
|---|---|---|---|---|---|---|
| GPT-5.5 | 22.2 | N/A | Independent | low | N/A | epoch.ai |
| GPT-5.4 | 21.7 | N/A | Independent | low | N/A | epoch.ai |
| GPT-5.1 | 17.3 | N/A | Independent | low | N/A | epoch.ai |
| Claude Opus 4.6 | 17.0 | N/A | Independent | low | N/A | epoch.ai |
| Gemini 3.1 Pro | 16.9 | N/A | Independent | low | N/A | epoch.ai |
| DeepSeek V4 Pro | 13.5 | N/A | Independent | low | N/A | epoch.ai |
| Kimi K2.5 | 13.2 | N/A | Independent | low | N/A | epoch.ai |
| Qwen3.5 Plus | 12.4 | N/A | Independent | low | N/A | epoch.ai |
| Grok 4.20 | 11.9 | N/A | Independent | low | N/A | epoch.ai |
| zai-org/GLM-4.7 | 10.9 | N/A | Independent | low | N/A | epoch.ai |
| DeepSeek V3.2 | 9.5 | N/A | Independent | low | N/A | epoch.ai |
| DeepSeek V3.2 | 7.4 | N/A | Independent | low | N/A | epoch.ai |
| MiMo V2 Pro | 6.9 | N/A | Independent | low | N/A | epoch.ai |
| MiniMax M2.5 | 6.3 | N/A | Independent | low | N/A | epoch.ai |
Every number links to where it was published. Low-confidence rows are muted and need per-cell verification.
Reproduced by the community
All runsLoading community runs…
About
CL-bench Life: Can Language Models Learn from Real-Life Context?
Dataset Description
CL-bench Life extends context learning evaluation to real-life scenarios. Unlike professional/domain-specific benchmarks, CL-bench Life contexts are messy, fragmented, and grounded in everyday experience, reflecting the kind of data people actually deal with daily. CL-bench Life is part of the CL-bench family of benchmarks for context learning.
Dataset Statistics
Total…