Meta / MODEL EVIDENCE
1 benchmarks · 2 observations · 1 sources
1 benchmarks · large dot: Llama 3-70B-Instruct-T-one; small dots: closest models where reported
Llama-3-70B-Instruct-T-one · ChemBench · Overall accuracy · published model comparison ↗
59% · Llama-3-70B-Instruct-T-one · ChemBench · Human-evaluation subset · accuracy · published model comparison · Are large language models superhuman chemists? ↗
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
1 of 1 shared benchmark comparisons
1 of 1 shared benchmark comparisons
1 of 1 shared benchmark comparisons
Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.
Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.
Adrian Mirza, Nawaf Alampara, Sreekanth Kunchapu, Martiño Ríos-García, Benedict Emoekabu, Aswanth Krishnan, Tanya Gupta, Mara Schilling-Wilhelmi, Macjonathan Okereke, Anagha Aneesh, Amir Mohammad Elahi, Mehrdad Asgari, Juliane Eberhardt, Hani M. Elbeheiry, María Victoria Gil, Maximilian Greiner, Caroline T. Holick, Christina Glaubitz, Tim Hoffmann, Abdelrahman Ibrahim, Lea C. Klepsch, Yannik Köster, Fabian Alexander Kreth, Jakob Meyer, Santiago Miret, Jan Matthias Peschel, Michael Ringleb, Nicole Roesner, Johanna Schreiber, Ulrich S. Schubert, Leanne M. Stafast, Dinga Wonanke, Michael Pieler, Philippe Schwaller, Kevin Maik Jablonka
Llama-3-70B-Instruct-T-one