Codesota · Models · Llama-2-70B-chatMeta AI3 results · 1 benchmarks
Model card

Llama-2-70B-chat.

Meta AIopen-sourceLlama 2 70B with RLHF chat fine-tuning

Meta Llama 2 70B chat model. 7-shot in-context learning evaluation on CNN/DailyMail reported in arXiv:2507.05123 (Jul 2025). Best overall ICL result in that study.

§ 01 · Benchmarks

Every benchmark Llama-2-70B-chat has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01cnn-/-daily-mailComputer Vision · Optical Character Recognitionrouge-141.0%#22/332025-07-01source ↗
02cnn-/-daily-mailComputer Vision · Optical Character Recognitionrouge-217.2%#25/332025-07-01source ↗
03cnn-/-daily-mailComputer Vision · Optical Character Recognitionrouge-l27.5%#31/332025-07-01source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area

Where Llama-2-70B-chat actually performs.

Computer Vision
1
benchmark
avg rank #26.0
§ 03 · Papers

1 paper with results for Llama-2-70B-chat.

  1. 2025-07-01· Natural Language Processing· 3 results

    An Evaluation of Large Language Models on Text Summarization Tasks Using Prompt Engineering Techniques

§ 04 · Related models

Other Meta AI models scored on Codesota.

GENRE
1 result · 1 SOTA
SeamlessM4T v2 Large
2.3B params · 1 result · 1 SOTA
DINOv2 (ViT-g) + Linear
Unknown params · 1 result
Fairseq S2T (MuST-C)
~150M params · 1 result
Mask2Former (Swin-L)
Unknown params · 1 result
MusicGen Large
3.3B params · 1 result
Voicebox
330M params · 1 result
convnext_base.fb_in22k_ft_in1k
1 result
§ 05 · Sources & freshness

Where these numbers come from.

arxiv
3
results
3 of 3 rows marked verified.