Codesota · Models · GPT-3.5-Turbo + TriSum RationaleOpenAI3 results · 1 benchmarks
Model card

GPT-3.5-Turbo + TriSum Rationale.

OpenAIproprietaryGPT-3.5-Turbo prompted with structured aspect-triple rationale

GPT-3.5-Turbo prompted with the structured TriSum rationale (aspect-triple-summary format). Reported in TriSum (arXiv:2403.10351, NAACL 2024) Table 2. Best ROUGE-1 result in the TriSum paper.

§ 01 · Benchmarks

Every benchmark GPT-3.5-Turbo + TriSum Rationale has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01cnn-/-daily-mailComputer Vision · Optical Character Recognitionrouge-223.5%#3/332024-03-15source ↗
02cnn-/-daily-mailComputer Vision · Optical Character Recognitionrouge-146.7%#4/332024-03-15source ↗
03cnn-/-daily-mailComputer Vision · Optical Character Recognitionrouge-l40.7%#12/332024-03-15source ↗
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 GPT-3.5-Turbo + TriSum Rationale actually performs.

Computer Vision
1
benchmark
avg rank #6.3
§ 03 · Papers

1 paper with results for GPT-3.5-Turbo + TriSum Rationale.

  1. 2024-03-15· Natural Language Processing· 3 results

    TriSum: Learning Summarization Ability from Large Language Models with Structured Rationale

§ 04 · Related models

Other OpenAI models scored on Codesota.

GPT-4o
Undisclosed params · 35 results · 9 SOTA
o3
16 results · 5 SOTA
o4-mini
13 results · 3 SOTA
o3 (high)
2 results · 1 SOTA
o4-mini (high)
1 result · 1 SOTA
o1
11 results
GPT-5
8 results
o1-preview
Undisclosed params · 8 results
§ 05 · Sources & freshness

Where these numbers come from.

arxiv
3
results
3 of 3 rows marked verified.