Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Procedural Reasoning on RecipeQA
Loading...
46.6
BertScore
GPT-4o
15.608
23.654
31.7
39.746
May 14, 2026
BertScore
LLM-Score
Updated 2mo ago
Evaluation Results
Method
Method
Links
BertScore
LLM-Score
GPT-4o
Framework=CoP
2026.05
46.6
49.7
Gemini-2.5
Framework=Baseline
2026.05
42.8
47.2
GPT-4o
Framework=Baseline
2026.05
38.7
48.6
Gemini-2.5
Framework=CoP
2026.05
37.8
44.6
Qwen2.5-72B
Framework=CoP
2026.05
26.5
32.3
Qwen2.5-72B
Framework=Baseline
2026.05
23.9
35
GPT-4o-mini
Framework=CoP
2026.05
22
29.6
GPT-4o-mini
Framework=Baseline
2026.05
20.7
31.9
Claude-3-5
Framework=CoP
2026.05
19.3
33.6
Claude-3-5
Framework=Baseline
2026.05
16.8
26.3
Feedback
Search any
task
Search any
task