Noometry

Model comparison

GPT-5 Mini vs Yi-34B

GPT-5 Mini is the stronger model overall, scoring 41.8 to 27.8 on the Noometry Index.

Last verified . 20 shared benchmarks.

GPT-5 Mini OpenAI

41.8

Rank #128 Confirmed

Yi-34B 01.AI

27.8

Rank #329 Confirmed

Summary

  • They share 20 benchmarks with published results for both. GPT-5 Mini scores higher in 8 categories and Yi-34B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GPT-5 Mini leads 45.6 to 7.5.
  • The biggest single-benchmark swing is MATH Level 5: 97.8% for GPT-5 Mini and 5.1% for Yi-34B.
  • Yi-34B has downloadable open weights; the other is API-only.

Side by side

GPT-5 MiniYi-34B
ProviderOpenAI01.AI
Noometry Index41.827.8
Released2025-08-072023-11-02
WeightsProprietaryOpen
Context window400K—
Max output128K—
Input $ / M tokens$0.25—
Output $ / M tokens$2—
Results tracked6023

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

Category by category

Coding GPT-5 Mini leads

GPT-5 Mini: 40.1 (#146), Yi-34B: 32.3 (#274)

BenchmarkGPT-5 MiniYi-34B
LMArena Coding14061112
SWE-bench Verified64.7%—
SWE-bench Verified (bash only)59.8%—
SWE-bench Multilingual39.7%—
SciCode39.2%—
WeirdML52.7%—
ALE-Bench799.77—
AlgoTune1.38—

Agentic & Tool Use Not comparable

GPT-5 Mini: 31.1 (#70), Yi-34B: —

BenchmarkGPT-5 MiniYi-34B
Terminal-Bench34.8%—
Berkeley Function Calling Leaderboard55.5%—
Vending-Bench 2-31.18—

Reasoning GPT-5 Mini leads

GPT-5 Mini: 23.9 (#168), Yi-34B: 21.2 (#226)

BenchmarkGPT-5 MiniYi-34B
LMArena Hard Prompts13801104
Epoch Capabilities Index145.52117.39
ARC-AGI-24.4%—
Kagi LLM Benchmark70.3%—
ARC-AGI-154.3%—
CritPt0%—
Chess Puzzles30%—
EnigmaEval8.2%—
Mystery Game Puzzles10%—
DTBench80.5%—
LMCA34.2%—
BIG-Bench Hard—71.7%
ForecastBench61—

Math GPT-5 Mini leads

GPT-5 Mini: 46.7 (#69), Yi-34B: 21.6 (#282)

BenchmarkGPT-5 MiniYi-34B
LMArena Math13781114
MATH Level 597.8%5.1%
FrontierMath (Tiers 1-3)46.7%—
FrontierMath Tier 412.2%—
OTIS Mock AIME 2024-202586.7%—
ProofBench9%—
Omni-MATH72.2%—
FrontierMath (Feb 2025 set)27.2%—
FrontierMath Tier 4 (v1)6.3%—
GSM8K—76%

Knowledge GPT-5 Mini leads

GPT-5 Mini: 45.6 (#86), Yi-34B: 7.5 (#309)

BenchmarkGPT-5 MiniYi-34B
GPQA Diamond75%14.7%
LMArena Expert13791061
Humanity's Last Exam19.4%—
SimpleQA Verified21.6%—
MMLU-Pro83.5%—
Confabulations13.3%—
Vectara Hallucination Rate12.9%—
GPQA (HELM)75.6%—
MMLU—76.3%

Multimodal Not comparable

GPT-5 Mini: 35.6 (#85), Yi-34B: —

BenchmarkGPT-5 MiniYi-34B
LMArena Vision1202—
VPCT40.2%—

Multilingual GPT-5 Mini leads

GPT-5 Mini: 48.9 (#137), Yi-34B: 29.7 (#264)

BenchmarkGPT-5 MiniYi-34B
LMArena Non-English13631079
LMArena Chinese13851176
LMArena French13861081
LMArena German13661042
LMArena Japanese1341993
LMArena Korean1308959
LMArena Russian13621050
LMArena Spanish13551070

Instruction Following GPT-5 Mini leads

GPT-5 Mini: 76.2 (#46), Yi-34B: 56.2 (#274)

BenchmarkGPT-5 MiniYi-34B
LMArena Instruction Following13571091
IFEval92.7%—

Long Context GPT-5 Mini leads

GPT-5 Mini: 41.9 (#132), Yi-34B: 33.2 (#264)

BenchmarkGPT-5 MiniYi-34B
LMArena Longer Query13551094
Fiction.LiveBench69.4%—

Writing & Preference GPT-5 Mini leads

GPT-5 Mini: 55.2 (#148), Yi-34B: 34.1 (#273)

BenchmarkGPT-5 MiniYi-34B
LMArena Text13731129
LMArena Creative Writing13251108
LMArena Multi-Turn13631113
Short-Story Creative Writing83.1%—
EQ-Bench Creative Writing1313—
WildBench85.5%—

Frequently asked questions

Is GPT-5 Mini better than Yi-34B?

GPT-5 Mini is the stronger model overall, scoring 41.8 to 27.8 on the Noometry Index.

Is GPT-5 Mini or Yi-34B better for coding?

GPT-5 Mini scores higher on coding benchmarks: 40.1 versus 32.3 in the Noometry coding category.

How many benchmarks do GPT-5 Mini and Yi-34B share?

20 benchmarks have published results for both models. GPT-5 Mini has 60 scored results on Noometry and Yi-34B has 23.

Related comparisons

Go deeper