Technology Innovation Institute·released 2024-05-091 source
Falcon 2 11B benchmark scores: 4 benchmarks tracked. 0% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 4 benchmarks·best result 77.21 on HellaSwag (self-reported)·0 of 4 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| HellaSwag | 77.21accuracy (%) | self-reported· optimizedT1 | 2024-05-09Falcon2-11B Technical Report |
| Winogrande | 56.6accuracy (%) | self-reported· optimizedT1 | 2024-05-09Falcon2-11B Technical Report |
| GSM8K | 53.83accuracy (%) | self-reported· optimizedT1 | 2024-05-09Falcon2-11B Technical Report |
| MMLU | 44.53accuracy (%) | self-reported· optimizedT1 | 2024-05-09Falcon2-11B Technical Report |
Claims drawn from cited facts, not live model generation.
This model was developed by Technology Innovation Institute and released in 2024. With 11 billion parameters, it is a mid-size model, balancing efficiency and lower cost against the reduced headroom of smaller-scale systems.
3 cited facts
This model is evaluated across four tracked benchmarks. It currently holds no top position on any of them. Because the reported numbers are self-reported rather than independently reproduced, treat them as claims, not verified results.
3 cited facts
With an average score gap of 29.02 points against the state of the art, this model sits well behind the leaders on its benchmarks. It holds the top score on none of the tracked benchmarks, meaning it has not demonstrated category-leading results.
2 cited facts
2 facts cross-checked across data sources: 2 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: curated_param_counts, epoch_benchmarks
Falcon 2 11B is an AI model developed by Technology Innovation Institute, released 2024-05-09. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Falcon 2 11B has recorded scores on 4 benchmarks, each shown with its evidence status.
Falcon 2 11B has recorded scores on 4 benchmarks — Winogrande, MMLU, GSM8K, HellaSwag. The full table above shows each score with its evidence status.
0 of 4 recorded scores (0%) are independently reproduced rather than self-reported by the lab.
Falcon 2 11B has 4 tracked claims: 4 self-reported.