supermarket

Language

Yi-34B-Chat

By 01.AI, in the Yi family.

Released
Nov 2023
Status
Legacy
Context
4.1K
Max output
—
Input per 1M tokens
—
Output per 1M tokens
—
Open weights
Yes
License
apache-2.0
Parameters
34B
Knowledge cutoff
—
Reasoning
No
Modalities
text → text

Category scores

Out of 100, from independent and third-party results only, by method category-2026-09-29.1.

Category scores
CategoryScoreRankCoverage
Human preference22.4Not ranked1 of 5

Benchmark results

Every result we hold for this model, with who ran it and where it was published.

Knowledge & reasoning

Knowledge & reasoning results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
BIG-Bench Hard (BBH)Average accuracy71.7%Self-reported——Yi: Open Foundation Models by 01.AI via Epoch AI
BIG-Bench Hard (BBH)Average accuracy51.4%Self-reported——Yi: Open Foundation Models by 01.AI via Epoch AI
MMLUAccuracy73.5%Self-reported——Yi: Open Foundation Models by 01.AI via Epoch AI
MMLUAccuracy67.6%Self-reported——Yi: Open Foundation Models by 01.AI via Epoch AI

Scientific reasoning

Scientific reasoning results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
GPQA DiamondAccuracy14.7%Independent—27 Jan 2025Epoch AI

Mathematics

Mathematics results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
GSM8KExact match76.0%Self-reported——Yi: Open Foundation Models by 01.AI via Epoch AI
GSM8KExact match71.7%Self-reported——Yi: Open Foundation Models by 01.AI via Epoch AI
MATH Level 5Accuracy5.1%Independent—27 Jan 2025Epoch AI

Human preference

Human preference results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Text Arena (arena.ai)Arena score (Elo scale)1184Independent—25 Sep 2026Arena
Text Arena (arena.ai)Votes15483Independent—25 Sep 2026Arena

Other Yi versions

Sources