Noometry

Model comparison

GPT-6 Sol vs Qwen1.5-110B

GPT-6 Sol is the stronger model overall, scoring 61.8 to 34.2 on the Noometry Index.

Last verified . 17 shared benchmarks.

GPT-6 Sol OpenAI

61.8

Rank #12 Confirmed

Qwen1.5-110B Alibaba (Qwen)

34.2

Rank #234 Confirmed

Summary

  • They share 17 benchmarks with published results for both. GPT-6 Sol scores higher in 8 categories and Qwen1.5-110B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6 Sol leads 87.2 to 33.7.
  • Qwen1.5-110B has downloadable open weights; the other is API-only.

Side by side

GPT-6 SolQwen1.5-110B
ProviderOpenAIAlibaba (Qwen)
Noometry Index61.834.2
Released2026-09-222024-04-25
WeightsProprietaryOpen
Context window1.05M—
Max output128K—
Input $ / M tokens$2—
Output $ / M tokens$10—
Results tracked4520

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

Category by category

Coding GPT-6 Sol leads

GPT-6 Sol: 60.1 (#11), Qwen1.5-110B: 33.0 (#264)

BenchmarkGPT-6 SolQwen1.5-110B
LMArena Coding14471184
DeepSWE68.8%—
FrontierCode49.3%—
LMArena WebDev1688—
SciCode57.6%—
BigCodeBench Instruct—35%
BigCodeBench Complete—44.4%
ALE-Bench2,462—

Agentic & Tool Use Not comparable

GPT-6 Sol: 37.2 (#36), Qwen1.5-110B: —

BenchmarkGPT-6 SolQwen1.5-110B
APEX-Agents54.3%—
GDP.pdf26.4%—
Vending-Bench 214,428—

Reasoning GPT-6 Sol leads

GPT-6 Sol: 74.0 (#9), Qwen1.5-110B: 22.7 (#189)

BenchmarkGPT-6 SolQwen1.5-110B
LMArena Hard Prompts14181168
ARC-AGI-289.6%—
NYT Connections (extended)90.1%—
ARC-AGI-195.5%—
CritPt30.9%—
EBR-Bench53.3%—
Mystery Game Puzzles56%—
DTBench97.3%—
LMCA59.1%—
Epoch Capabilities Index162.72—
ForecastBench—57.7

Math GPT-6 Sol leads

GPT-6 Sol: 87.2 (#7), Qwen1.5-110B: 33.7 (#201)

BenchmarkGPT-6 SolQwen1.5-110B
LMArena Math14021185
FrontierMath (Tiers 1-3)89.8%—
FrontierMath Tier 490%—
OTIS Mock AIME 2024-2025100%—
ProofBench83%—

Knowledge GPT-6 Sol leads

GPT-6 Sol: 64.8 (#15), Qwen1.5-110B: 31.2 (#219)

BenchmarkGPT-6 SolQwen1.5-110B
LMArena Expert14391144
GPQA Diamond94.3%—
SimpleQA Verified60.7%—
Vectara Hallucination Rate6.5%—

Multimodal Not comparable

GPT-6 Sol: 47.6 (#10), Qwen1.5-110B: —

BenchmarkGPT-6 SolQwen1.5-110B
LMArena Vision1245—
Blueprint-Bench 236.9%—
Furniture Assembly58.3%—

Multilingual GPT-6 Sol leads

GPT-6 Sol: 50.5 (#118), Qwen1.5-110B: 33.6 (#250)

BenchmarkGPT-6 SolQwen1.5-110B
LMArena Non-English13851142
LMArena Chinese14051206
LMArena French14101151
LMArena German13901123
LMArena Japanese13851074
LMArena Korean13411044
LMArena Russian14011118
LMArena Spanish13841142

Instruction Following GPT-6 Sol leads

GPT-6 Sol: 74.5 (#94), Qwen1.5-110B: 60.3 (#252)

BenchmarkGPT-6 SolQwen1.5-110B
LMArena Instruction Following14121158

Long Context GPT-6 Sol leads

GPT-6 Sol: 43.1 (#108), Qwen1.5-110B: 35.1 (#242)

BenchmarkGPT-6 SolQwen1.5-110B
LMArena Longer Query14111157

Writing & Preference GPT-6 Sol leads

GPT-6 Sol: 71.9 (#18), Qwen1.5-110B: 38.0 (#255)

BenchmarkGPT-6 SolQwen1.5-110B
LMArena Text13951175
LMArena Creative Writing13781148
LMArena Multi-Turn14121160
EQ-Bench Creative Writing2125—

Frequently asked questions

Is GPT-6 Sol better than Qwen1.5-110B?

GPT-6 Sol is the stronger model overall, scoring 61.8 to 34.2 on the Noometry Index.

Is GPT-6 Sol or Qwen1.5-110B better for coding?

GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 33.0 in the Noometry coding category.

How many benchmarks do GPT-6 Sol and Qwen1.5-110B share?

17 benchmarks have published results for both models. GPT-6 Sol has 45 scored results on Noometry and Qwen1.5-110B has 20.

Related comparisons

Go deeper