100-LongBench
Harbor: pending100-LongBench — AI evaluation benchmark listed by awesome.
Auto57%Long Context
- Samples
- N/A
- Released
- 2025
- Scores
- 0
How to run
ltb · ada-leval
$ npm i -g lettokenburn-cli$ ltb bench info ada-leval
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
9 sourced entries| Harness | Source | Confidence | Link | |||
|---|---|---|---|---|---|---|
| GPT-4 1106 Preview | 74.0 | N/A | Independent | medium | Mar 15, 2023 | arxiv.org |
| GPT-4 0125 Preview | 73.5 | N/A | Independent | medium | Mar 15, 2023 | arxiv.org |
| Claude 2 | 65.0 | N/A | Independent | medium | N/A | paperswithcode.com |
| GPT-3.5-Turbo-1106 | 61.5 | N/A | Independent | medium | N/A | paperswithcode.com |
| InternLM2-7b | 58.6 | N/A | Independent | medium | Mar 26, 2024 | arxiv.org |
| Vicuna-13b-v1.5-16k | 53.4 | N/A | Independent | medium | Jun 9, 2023 | arxiv.org |
| ChatGLM3-6b-32k | 39.8 | N/A | Independent | medium | Oct 5, 2022 | arxiv.org |
| Vicuna-7b-v1.5-16k | 37.0 | N/A | Independent | medium | Jun 9, 2023 | arxiv.org |
| ChatGLM2-6b-32k | 31.2 | N/A | Independent | medium | Oct 5, 2022 | arxiv.org |
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
Ada-LEval — AI evaluation benchmark listed by awesome.