0A
01.AI
Language model · China ·May 2024

Yi-1.5-34B

Language Open (Restricted)
34B
Parameters
18
Benchmarks

About Yi-1.5-34B

Yi-1.5-34B is an AI model developed by 01.AI, in the language category, released in 2024, made available as an open-weights model with 34B params.

On this page you'll find Yi-1.5-34B's full specifications, including 18 benchmark results. Review provider pricing and benchmark scores below, or compare Yi-1.5-34B head-to-head with other language models.

Links

Run Yi-1.5-34B locally — what to buy

Share this build ↗

Sized to what Yi-1.5-34B actually needs (~8k context at Q4), not to the biggest GPU: Good = cheapest that runs it, Better = best value, Best = most headroom. Speed is a hardware estimate; anything past ~120 tok/s is shown as instant.

Software support

✓ measured · · compatible · — not supported. Informational only — speed is hardware-based.

Community

Would you run Yi-1.5-34B again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

Yi-1.5-34B benchmark scores
Benchmark Category Score Variant
HumanEval code 46.3% cited-qwen2-57b
MBPP code 65.5% cited-qwen2-57b
EvalPlus coding 51.9 cited-qwen2-57b
MultiPL-E coding 39.5 cited-qwen2-57b
AlpacaEval 2 general 34.8% instruct-cited-exaone35
ArenaHard general 23.1% instruct-cited-exaone35
IFEval general 55.5% instruct-cited-exaone35
LiveBench general 26.2 instruct-cited-exaone35
MMLU general 77.1% cited-qwen2-57b
MMLU-Pro general 48.3% cited-qwen2-57b
ARC-Challenge knowledge 65.6 cited-qwen2-57b
CMMLU knowledge 84.8 cited-qwen2-57b
GSM8K math 82.7% cited-qwen2-57b
MATH math 41.7% cited-qwen2-57b
BIG-Bench Hard reasoning 76.4% cited-qwen2-57b
HellaSwag reasoning 85.9 cited-qwen2-57b
Winogrande reasoning 84.9 cited-qwen2-57b
TruthfulQA safety 53.9% cited-qwen2-57b

More models like Yi-1.5-34B

Frequently asked questions

What is Yi-1.5-34B?

Yi-1.5-34B is an AI model developed by 01.AI, in the language category, released in 2024. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Yi-1.5-34B?

Yi-1.5-34B was developed by 01.AI and released in 2024.

Is Yi-1.5-34B open source or proprietary?

Yi-1.5-34B ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.

How much does Yi-1.5-34B cost?

Pricing for Yi-1.5-34B depends on the provider. See the providers table on this page for the latest API rates.

How does Yi-1.5-34B perform on benchmarks?

Yi-1.5-34B is benchmarked across 18 evaluations on GenAIList, including HumanEval (46.3%). See the full benchmark table below and compare it with other models.

No videos yet. Know a good one? Add it below.

Know a great video about Yi-1.5-34B?