CorpFin v2 ↗38.85 %
Llama 3.1 Instruct Turbo (70B) · CorpFin · Accuracy ↗
Meta / MODEL EVIDENCE
Llama 3.1 Instruct Turbo (70B)
5 benchmarks · 9 observations · 5 sources
Scores at a glance
5 benchmarks · large dot: Llama 3.1 Instruct Turbo (70B); small dots: closest models where reported
MortgageTax & TaxEval v2 ↗56.17 %
Llama 3.1 Instruct Turbo (70B) · TaxEval · Accuracy ↗
MedQA (USMLE) ↗84.78 %
Llama 3.1 Instruct Turbo (70B) · MedQA · Accuracy ↗
MATH-500 ↗65 %
Llama 3.1 Instruct Turbo (70B) · MATH 500 · Accuracy ↗
Llama 3.1 Instruct Turbo (70B) · MMLU-Redux (2.0) · Virology · corrected-instance accuracy · MMLU-Redux 2.0 paper · audited subject comparison ↗
4 more reported results
96% · Llama 3.1 Instruct Turbo (70B) · MMLU-Redux (2.0) · Logical Fallacies · corrected-instance accuracy · MMLU-Redux 2.0 paper · audited subject comparison · Are We Done with MMLU? ↗
64% · Llama 3.1 Instruct Turbo (70B) · MMLU-Redux (2.0) · College Chemistry · corrected-instance accuracy · MMLU-Redux 2.0 paper · audited subject comparison · Are We Done with MMLU? ↗
65% · Llama 3.1 Instruct Turbo (70B) · MMLU-Redux (2.0) · Professional Law · corrected-instance accuracy · MMLU-Redux 2.0 paper · audited subject comparison · Are We Done with MMLU? ↗
96% · Llama 3.1 Instruct Turbo (70B) · MMLU-Redux (2.0) · Human Sexuality · corrected-instance accuracy · MMLU-Redux 2.0 paper · audited subject comparison · Are We Done with MMLU? ↗
Closest models by score
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
3 of 4 shared benchmark comparisons
Claude 3.5 Haiku Latest →Anthropic
3 of 4 shared benchmark comparisons
3 of 4 shared benchmark comparisons
How similarity is measured
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.
Sources
Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.
- Are We Done with MMLU? — published result table ↗
All 16 authors
Gema, Aryo Pradipta, Leang, Joshua Ong Jun, Hong, Giwon, Devoto, Alessio, Mancino, Alberto Carlo Maria, Saxena, Rohit, He, Xuanli, Zhao, Yu, Du, Xiaotang, Madani, Mohammad Reza Ghasemi, Barale, Claire, McHardy, Robert, Harris, Joshua, Kaddour, Jean, van Krieken, Emile, Minervini, Pasquale
- CorpFin — evaluation methodology and results ↗
- MATH 500 — evaluation methodology and results ↗
- MedQA — evaluation methodology and results ↗
- TaxEval — evaluation methodology and results ↗
Names used in source tables
Llama 3.1 Instruct Turbo (70B)