all the models — AI benchmark observatory
← Models

Qwen2 72B Instruct

Alibaba Cloud / Qwen Team · open weight · qwen2-72b-instruct

Qwen2-72B-Instruct is an instruction-tuned language model with 72 billion parameters, supporting a context length of up to 131,072 tokens. It's part of the new Qwen2 series, which has surpassed most open-source models and demonstrates competitiveness against proprietary models across various benchmarks.

GSM8kHumanEvalMMLUEvalPlusMMLU-ProMATH

Benchmark scores

BenchmarkScore
GSM8k0.91
HumanEval0.86
MMLU0.82
EvalPlus0.79
MMLU-Pro0.64
MATH0.60
GPQA0.42

Pricing

  • No provider pricing.

AA metrics

No Artificial Analysis link yet.

Arena Elo

  • No Arena snapshot linked.
Qwen2 72B Instruct Benchmarks · all the models