Benchmark
BABILong avg(qa1-5) 128k
Long context benchmarks measure how well models use information in long inputs. Scores are percentages. Higher is better.
All long context benchmarksScores from BABILong v0 data docs.
- Models and systems measured
- 10
- Scores recorded
- 10
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 46.3%
- Mean
- 45%
- Median
- 28.2%
- Std dev
- 13%
- 10th percentile
- 92.5%
- 90th percentile
- 7%
- Min
Results
The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.
| Model or system | Score |
|---|---|
| ~ ARMT (137M) fine-tuneavg, 128k· BABILong v0 data docs | 96.9% |
| ~ Mamba (130M) fine-tuneavg, 128k· BABILong v0 data docs | 92.5% |
| ~ RMT (137M) fine-tuneavg, 128k· BABILong v0 data docs | 58.5% |
| ChatGLM3 6Bchatglm3-6b-128k, avg, 128k· BABILong v0 data docs | 13% |
| GPT-4-0125-previewavg, 128k· BABILong v0 data docs | 36% |
| Llama 3.1 70B InstructMeta-Llama-3.1-70B-Instruct, avg, 128k· BABILong v0 data docs | 45% |
| Llama 3.1 8B InstructMeta-Llama-3.1-8B-Instruct, avg, 128k· BABILong v0 data docs | 39% |
| Llama3-ChatQA-1.5-8B + RAGavg, 128k· BABILong v0 data docs | 45% |
| Phi-3 Medium 128K InstructPhi-3-medium-128k-instruct, avg, 128k· BABILong v0 data docs | 30% |
| Phi-3 Mini 128K InstructPhi-3-mini-128k-instruct, avg, 128k· BABILong v0 data docs | 7% |
Data credits: RMT-team, Kuratov et al. Official v0 numeric CSV; results licence not separately stated.