Noometry

Model comparison

GPT-5.6 Luna vs Yi-34B

GPT-5.6 Luna is the stronger model overall, scoring 54.7 to 27.4 on the Noometry Index.

Last verified . 19 shared benchmarks.

GPT-5.6 Luna OpenAI

54.7

Rank #24 Confirmed

Yi-34B 01.AI

27.4

Rank #325 Confirmed

Summary

  • They share 19 benchmarks with published results for both. GPT-5.6 Luna 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-5.6 Luna leads 77.5 to 19.8.
  • The biggest single-benchmark swing is GPQA Diamond: 91.6% for GPT-5.6 Luna and 14.7% for Yi-34B.
  • Yi-34B has downloadable open weights; the other is API-only.

Side by side

GPT-5.6 LunaYi-34B
ProviderOpenAI01.AI
Noometry Index54.727.4
Released2026-07-092023-11-02
WeightsProprietaryOpen
Context window1.05M—
Max output128K—
Input $ / M tokens$0.20—
Output $ / M tokens$1.20—
Results tracked5123

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

Category by category

Coding GPT-5.6 Luna leads

GPT-5.6 Luna: 53.9 (#25), Yi-34B: 31.8 (#269)

BenchmarkGPT-5.6 LunaYi-34B
LMArena Coding14661112
DeepSWE67.2%—
FrontierCode39.8%—
CursorBench35.9%—
LMArena WebDev1517—
SciCode53.6%—
WeirdML60.9%—
ALE-Bench1,667—

Agentic & Tool Use Not comparable

GPT-5.6 Luna: 35.3 (#37), Yi-34B: —

BenchmarkGPT-5.6 LunaYi-34B
BALROG45.6%—
GDP.pdf22.7%—
Vending-Bench 24,095—

Reasoning GPT-5.6 Luna leads

GPT-5.6 Luna: 47.5 (#38), Yi-34B: 20.3 (#222)

BenchmarkGPT-5.6 LunaYi-34B
LMArena Hard Prompts14521104
Epoch Capabilities Index156.32117.28
ARC-AGI-259.5%—
SimpleBench46.8%—
Kagi LLM Benchmark49.1%—
NYT Connections (extended)69.4%—
ARC-AGI-188%—
CritPt20.6%—
Chess Puzzles40%—
Mystery Game Puzzles21%—
DTBench89.1%—
LMCA48.5%—
Surface Evolver Bench61.9%—
BIG-Bench Hard—71.7%

Math GPT-5.6 Luna leads

GPT-5.6 Luna: 77.5 (#12), Yi-34B: 19.8 (#277)

BenchmarkGPT-5.6 LunaYi-34B
LMArena Math14551114
FrontierMath (Tiers 1-3)82.1%—
FrontierMath Tier 461%—
OTIS Mock AIME 2024-202598.3%—
ProofBench60%—
MATH Level 5—5.1%
GSM8K—76%

Knowledge GPT-5.6 Luna leads

GPT-5.6 Luna: 58.6 (#31), Yi-34B: 7.5 (#304)

BenchmarkGPT-5.6 LunaYi-34B
GPQA Diamond91.6%14.7%
LMArena Expert14791061
SimpleQA Verified41%—
MMLU—76.3%

Multimodal Not comparable

GPT-5.6 Luna: 43.0 (#22), Yi-34B: —

BenchmarkGPT-5.6 LunaYi-34B
LMArena Vision1259—
Blueprint-Bench 222.6%—
Furniture Assembly42.5%—
LMArena Document1457—

Multilingual GPT-5.6 Luna leads

GPT-5.6 Luna: 53.0 (#73), Yi-34B: 29.9 (#259)

BenchmarkGPT-5.6 LunaYi-34B
LMArena Non-English14181079
LMArena Chinese14691175
LMArena French14571080
LMArena German14591042
LMArena Japanese1416993
LMArena Korean1414959
LMArena Russian14281050
LMArena Spanish14451070

Instruction Following GPT-5.6 Luna leads

GPT-5.6 Luna: 76.0 (#48), Yi-34B: 56.4 (#269)

BenchmarkGPT-5.6 LunaYi-34B
LMArena Instruction Following14401091

Long Context GPT-5.6 Luna leads

GPT-5.6 Luna: 43.9 (#78), Yi-34B: 33.2 (#259)

BenchmarkGPT-5.6 LunaYi-34B
LMArena Longer Query14371094

Writing & Preference GPT-5.6 Luna leads

GPT-5.6 Luna: 68.3 (#27), Yi-34B: 34.3 (#268)

BenchmarkGPT-5.6 LunaYi-34B
LMArena Text14321129
LMArena Creative Writing13971108
LMArena Multi-Turn14331113
EQ-Bench Creative Writing1829—
EQ-Bench 41156—

Frequently asked questions

Is GPT-5.6 Luna better than Yi-34B?

GPT-5.6 Luna is the stronger model overall, scoring 54.7 to 27.4 on the Noometry Index.

Is GPT-5.6 Luna or Yi-34B better for coding?

GPT-5.6 Luna scores higher on coding benchmarks: 53.9 versus 31.8 in the Noometry coding category.

How many benchmarks do GPT-5.6 Luna and Yi-34B share?

19 benchmarks have published results for both models. GPT-5.6 Luna has 51 scored results on Noometry and Yi-34B has 23.

Related comparisons

Go deeper