Gemma 2 27B

Gemma 2 27B IT is an instruction-tuned version of Google's state-of-the-art open language model. Built from the same research and technology as Gemini, it's optimized for dialogue applications through supervised fine-tuning, distillation from larger models, and RLHF.

ARC-E

88.6%

i
HellaSwag

86.4%

i
BoolQ

84.8%

i
TriviaQA

83.7%

i
Winogrande

83.7%

i
PIQA

83.2%

i
MMLU

75.2%

i
BIG-Bench

74.9%

i
GSM8k

74.0%

i
ARC-C

71.4%

i
MBPP

62.6%

i
AGIEval

55.1%

i
Social IQa

53.7%

i
HumanEval

51.8%

i
MATH

42.3%

i
Natural Questions

34.5%

i

Pricing, uptime, and speed via OpenRouter — updated Jul 17, 2026, 04:19 AM.

Provider	Status	Input	Output	Limits	Uptime	Speed	Notes
NextBit	available	$0.65/Mtok	$0.65/Mtok	8K tokens context 2K tokens max output	—	1,008 ms p50 TTFT 26 tok/s p50	int4