Mixtral_AI_CyberTron_DeepMind_III_UFT Benchmark Results

Mixtral_AI_CyberTron_DeepMind_III_UFT: benchmark results

Provider: Mistral.

Aggregate Rating 1393 ± 30, rank #6396 of 10916 rated models, from 12 benchmark results.

Benchmark	Score	Metric	Percentile
Open CoT - LSAT Reading Comprehension	15.99	CoT Gain (%)	69.8
Open LLM Leaderboard v1 - GSM8K	51.86	Accuracy (%) (5-shot)	63.8
Open LLM Leaderboard v1 - WinoGrande	77.98	Accuracy (%) (5-shot)	59.9
Open LLM Leaderboard v1 - HellaSwag	83.15	Normalized accuracy (%) (10-shot)	56.4
Open LLM Leaderboard v1 - ARC Challenge	61.86	Normalized accuracy (%) (25-shot)	54.8
Open LLM Leaderboard v1 - MMLU	61.95	Accuracy (%) (5-shot)	53.5
Open LLM Leaderboard v1 - TruthfulQA MC2	49.41	MC2 (%) (0-shot)	44.7
Open CoT Leaderboard	5.73	Average CoT Gain (%)	38.2
Open CoT - LSAT Logical Reasoning	7.65	CoT Gain (%)	35.5
Open CoT - LogiQA 2	3.94	CoT Gain (%)	29.8
Open CoT - LSAT Analytical Reasoning	0.43	CoT Gain (%)	10.3
Open CoT - LogiQA	0.64	CoT Gain (%)	9.2