Yi-1.5-34B-Chat: benchmark scores, price and ranking

Yi-1.5-34B-Chat from 01.AI ranks #638 of 743 LLMs on the LLMs Tiger aggregate benchmark score (44.4), based on 2 benchmark results captured up to 2026-10-13.

Organisation: 01.AI
Type: Open-weight / local model
Open weights: Yes
Released: 2024-05-13 (source: epoch)
Aggregate rank: #638 of 743 (score 44.4)

Across the 2 benchmarks where at least ten models are scored, Yi-1.5-34B-Chat is in the top 10% on 0 and in the top half on 0.

Yi-1.5-34B-Chat benchmark results

Yi-1.5-34B-Chat benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
MMLU-Pro	52.3%	#74 of 136	HuggingFace MMLU-Pro leaderboard	2026-10-13
GPQA Diamond	32.0%	#244 of 275	Epoch AI Benchmarking Hub	2026-10-13

About Yi-1.5-34B-Chat

Yi-1.5-34B-Chat is an open-weight model that can run on your own hardware from 01.AI. It was released on 2024-05-13, according to Epoch AI. No API price is listed for it yet. We hold 2 benchmark results for it across 1 area, and none is in the top tenth of its board.

Where Yi-1.5-34B-Chat stands

On our aggregate score, Yi-1.5-34B-Chat is #638 of 743 ranked models, in the lower half. Its score is 44.4; the scale is centred on 50, so it sits 5.6 points below the typical model. That beats 14% of the ranked field. Among the 4 ranked 01.AI models it is #2. The next one up is Yi-34B at 46.2. The next one down is Yi-34B-Chat at 44.0.

Yi-1.5-34B-Chat, benchmark by benchmark

Yi-1.5-34B-Chat lands below the middle on MMLU-Pro: 52.3%, #74 of 136, with 54% of the field scoring higher. Darwin-180B-RSI leads at 88.1%; the closest result above is Llama 3.1-70B at 52.5%. It covers 57-subject knowledge + reasoning. The board median is 55.3%, so Yi-1.5-34B-Chat is 3.0 points below it. Source: HuggingFace MMLU-Pro leaderboard, captured 2026-10-13.

GPQA Diamond is a weak spot. Yi-1.5-34B-Chat scores 32.0%, #244 of 275, behind 88% of the models measured. The leader, GPT-6 Astra (max), reaches 95.8%. It covers expert-level science questions. The board median is 71.7%, so Yi-1.5-34B-Chat is 39.7 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Strengths and weaknesses

Reasoning, maths and science: weak, ahead of 28% of the field on average across 2 benchmarks. Its best board here is MMLU-Pro (#74 of 136) and its weakest is GPQA Diamond (#244 of 275).

Release history

The 01.AI model released before it was Yi 6B on 2023-11-22, which scores 44.0.

Reading these numbers

The 2 scores on this page come from 2 sources: Epoch AI Benchmarking Hub (1), HuggingFace MMLU-Pro leaderboard (1). No official leaderboard supplied any of them, so treat them as third-party measurements. With 2 results the aggregate rank can move a lot when one new score arrives.

Models ranked nearby

#635 c4ai-command-a-03-2025 (44.5)
#636 DeepSeek-V3.2 (Thinking; Novita) (44.5)
#637 mistral-small-3.1-2503 (44.4)
#639 granite-4.1-3b (44.4)
#640 Laguna M.1 (44.4)
#641 grok-code-fast-1 (44.3)