Noometry

Model comparison

GPT-6 Astra vs Yi-34B

GPT-6 Astra is the stronger model overall, scoring 70.8 to 27.8 on the Noometry Index.

Last verified . 19 shared benchmarks.

GPT-6 Astra OpenAI

70.8

Rank #1 Confirmed

Yi-34B 01.AI

27.8

Rank #329 Confirmed

Summary

  • They share 19 benchmarks with published results for both. GPT-6 Astra scores higher in 8 categories and Yi-34B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6 Astra leads 93.5 to 21.6.
  • The biggest single-benchmark swing is GPQA Diamond: 95.8% for GPT-6 Astra and 14.7% for Yi-34B.
  • Yi-34B has downloadable open weights; the other is API-only.

Side by side

GPT-6 AstraYi-34B
ProviderOpenAI01.AI
Noometry Index70.827.8
Released2026-09-032023-11-02
WeightsProprietaryOpen
Context window1.05M—
Max output128K—
Input $ / M tokens$10—
Output $ / M tokens$50—
Results tracked5623

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding GPT-6 Astra leads

GPT-6 Astra: 73.7 (#2), Yi-34B: 32.3 (#274)

BenchmarkGPT-6 AstraYi-34B
LMArena Coding14871112
DeepSWE74.1%—
FrontierCode53.3%—
LMArena WebDev1786—
FrontierSWE65.5%—
SciCode56.5%—
GSO79.4%—
WeirdML93.6%—
MirrorCode46.7%—
ALE-Bench2,951—

Agentic & Tool Use Not comparable

GPT-6 Astra: 52.9 (#3), Yi-34B: —

BenchmarkGPT-6 AstraYi-34B
APEX-Agents64.7%—
Remote Labor Index20.8%—
BALROG68.3%—
GDP.pdf34.2%—
Vending-Bench 215,515—

Reasoning GPT-6 Astra leads

GPT-6 Astra: 85.1 (#1), Yi-34B: 21.2 (#226)

BenchmarkGPT-6 AstraYi-34B
LMArena Hard Prompts14621104
Epoch Capabilities Index166.45117.39
ARC-AGI-295%—
NYT Connections (extended)98.1%—
ARC-AGI-198.5%—
CritPt31.7%—
Chess Puzzles72%—
EBR-Bench76.2%—
Mystery Game Puzzles84%—
DTBench97.3%—
LMCA64.4%—
Bench to the Future 30.14—
BIG-Bench Hard—71.7%

Math GPT-6 Astra leads

GPT-6 Astra: 93.5 (#2), Yi-34B: 21.6 (#282)

BenchmarkGPT-6 AstraYi-34B
LMArena Math14651114
FrontierMath (Tiers 1-3)93.7%—
FrontierMath Tier 497.6%—
OTIS Mock AIME 2024-2025100%—
ProofBench99%—
MATH Level 5—5.1%
FrontierMath Erdős2.9%—
GSM8K—76%

Knowledge GPT-6 Astra leads

GPT-6 Astra: 75.3 (#1), Yi-34B: 7.5 (#309)

BenchmarkGPT-6 AstraYi-34B
GPQA Diamond95.8%14.7%
LMArena Expert14831061
Humanity's Last Exam54.8%—
SimpleQA Verified75.6%—
Vectara Hallucination Rate8.7%—
MMLU—76.3%

Multimodal Not comparable

GPT-6 Astra: 55.0 (#3), Yi-34B: —

BenchmarkGPT-6 AstraYi-34B
LMArena Vision1281—
Blueprint-Bench 249.7%—
Furniture Assembly80%—
LMArena Document1468—

Multilingual GPT-6 Astra leads

GPT-6 Astra: 53.7 (#61), Yi-34B: 29.7 (#264)

BenchmarkGPT-6 AstraYi-34B
LMArena Non-English14301079
LMArena Chinese14841176
LMArena French14561081
LMArena German14401042
LMArena Japanese1379993
LMArena Korean1426959
LMArena Russian14361050
LMArena Spanish14071070

Instruction Following GPT-6 Astra leads

GPT-6 Astra: 76.3 (#44), Yi-34B: 56.2 (#274)

BenchmarkGPT-6 AstraYi-34B
LMArena Instruction Following14501091

Long Context GPT-6 Astra leads

GPT-6 Astra: 44.5 (#62), Yi-34B: 33.2 (#264)

BenchmarkGPT-6 AstraYi-34B
LMArena Longer Query14561094

Writing & Preference GPT-6 Astra leads

GPT-6 Astra: 75.3 (#7), Yi-34B: 34.1 (#273)

BenchmarkGPT-6 AstraYi-34B
LMArena Text14411129
LMArena Creative Writing14181108
LMArena Multi-Turn14481113
EQ-Bench Creative Writing2173—

Frequently asked questions

Is GPT-6 Astra better than Yi-34B?

GPT-6 Astra is the stronger model overall, scoring 70.8 to 27.8 on the Noometry Index.

Is GPT-6 Astra or Yi-34B better for coding?

GPT-6 Astra scores higher on coding benchmarks: 73.7 versus 32.3 in the Noometry coding category.

How many benchmarks do GPT-6 Astra and Yi-34B share?

19 benchmarks have published results for both models. GPT-6 Astra has 56 scored results on Noometry and Yi-34B has 23.

Related comparisons

Go deeper