What are Yi-34B's benchmark scores?

As of 25 Oct 2026, Yi-34B scores 35.0 ±4.8 on the BenchLeader Index, strongest in human preference (31) and weakest in reasoning (20). That rests on 6 independent benchmark results, and every score on this page links to its publisher.

How does Yi-34B rank?

Yi-34B is #767 of 785 ranked configurations on 25 Oct 2026. 129 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.

When was Yi-34B released?

01.AI released Yi-34B on 2 Nov 2023.

01.AI Compare with another model

Yi-34B

Yi-34B is a 01.AI proprietary model, released 2 Nov 2023. Its best configuration ranks #767 of 785 on the BenchLeader Index at 35.0 ±4.8, in the lower half. The ± is the point: 129 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in human preference (31) and lowest in reasoning (20). Last measured 22 Oct 2026.

Blended price: –
Output speed: –
First answer: –
Context: –
Full answer: –
Cost per run: –
Released: 2 Nov 2023

How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.

Overall index35
Reasoning20
Coding30
Maths29
Human preference31

Versions

01.AI has shipped 2 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.

Model	Released	Index	Rank
Yi-1.5-34B	13 May 2024	39.2	#694
Yi-34Bthis page	2 Nov 2023	35.0	#767

How its index has moved

8 Sept 2026 to 19 Oct 2026

The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.

Benchmark results

See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

Benchmark	not stated	Source
GPQA Diamond	14.7%#290	Epoch AI Benchmarking Hub
Arena Hard Prompts	1184#323	Arena (LMArena)
BIG-Bench Hardnot in index	71.7%#10	Epoch AI Benchmarking Hub

Coding

Benchmark	not stated	Source	Trend
Arena Coding	1206#324	Arena (LMArena)

Maths

Benchmark	not stated	Source
MATH Level 5	5.2%#93	Epoch AI Benchmarking Hub
Arena Maths	1151#321	Arena (LMArena)
GSM8Knot in index	76.0%#20	Epoch AI Benchmarking Hub

Knowledge

Benchmark	not stated	Source	Trend
MMLUnot in index	76.3%#34	Epoch AI Benchmarking Hub

Instruction following

Benchmark	not stated	Source	Trend
Arena Instruction Followingnot in index	1152#325	Arena (LMArena)

Human preference

Benchmark	not stated	Source
Arena Text	1184#317	Arena (LMArena)
Arena Creative Writingnot in index	1154#314	Arena (LMArena)
Arena Multi-turnnot in index	1162#312	Arena (LMArena)
Arena Longer Queriesnot in index	1173#320	Arena (LMArena)

Composite

Benchmark	not stated	Source	Trend
Epoch Capabilities Indexnot in index	117.3#185	Epoch AI Benchmarking Hub

New this month

Questions people ask

What are Yi-34B's benchmark scores?: As of 25 Oct 2026, Yi-34B scores 35.0 ±4.8 on the BenchLeader Index, strongest in human preference (31) and weakest in reasoning (20). That rests on 6 independent benchmark results, and every score on this page links to its publisher.
How does Yi-34B rank?: Yi-34B is #767 of 785 ranked configurations on 25 Oct 2026. 129 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
When was Yi-34B released?: 01.AI released Yi-34B on 2 Nov 2023.

Data as of 25 Oct 2026. Compare with another model.

Cite as: BenchLeader, “Yi-34B: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/yi-34b.