Noometry

Model comparison

GPT-6 Sol vs Qwen2-72B

GPT-6 Sol is the stronger model overall, scoring 61.8 to 30.0 on the Noometry Index.

Last verified . 19 shared benchmarks.

GPT-6 Sol OpenAI

61.8

Rank #12 Confirmed

Qwen2-72B Alibaba (Qwen)

30.0

Rank #300 Confirmed

Summary

  • They share 19 benchmarks with published results for both. GPT-6 Sol scores higher in 9 categories and Qwen2-72B in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6 Sol leads 87.2 to 30.2.
  • The biggest single-benchmark swing is GPQA Diamond: 94.3% for GPT-6 Sol and 40.8% for Qwen2-72B.
  • Qwen2-72B has downloadable open weights; the other is API-only.

Side by side

GPT-6 SolQwen2-72B
ProviderOpenAIAlibaba (Qwen)
Noometry Index61.830.0
Released2026-09-222024-06-07
WeightsProprietaryOpen
Context window1.05M—
Max output128K—
Input $ / M tokens$2—
Output $ / M tokens$10—
Results tracked4526

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), Qwen2-72B: 29.1 (#310)

BenchmarkGPT-6 SolQwen2-72B
LMArena Coding14471196
DeepSWE68.8%—
FrontierCode49.3%—
LMArena WebDev1688—
SciCode57.6%—
WeirdML—11.3%
BigCodeBench Instruct—38.5%
BigCodeBench Complete—54%
ALE-Bench2,462—

Agentic & Tool Use GPT-6 Sol leads

GPT-6 Sol: 37.2 (#36), Qwen2-72B: 17.0 (#146)

BenchmarkGPT-6 SolQwen2-72B
APEX-Agents54.3%—
TheAgentCompany—1.1%
GDP.pdf26.4%—
METR Time Horizons—29.9%
Vending-Bench 214,428—

Reasoning GPT-6 Sol leads

GPT-6 Sol: 74.0 (#9), Qwen2-72B: 23.2 (#181)

BenchmarkGPT-6 SolQwen2-72B
LMArena Hard Prompts14181191
Epoch Capabilities Index162.72125.28
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%—

Math GPT-6 Sol leads

GPT-6 Sol: 87.2 (#7), Qwen2-72B: 30.2 (#236)

BenchmarkGPT-6 SolQwen2-72B
LMArena Math14021235
FrontierMath (Tiers 1-3)89.8%—
FrontierMath Tier 490%—
OTIS Mock AIME 2024-2025100%—
ProofBench83%—
MATH Level 5—39.1%

Knowledge GPT-6 Sol leads

GPT-6 Sol: 64.8 (#15), Qwen2-72B: 21.2 (#275)

BenchmarkGPT-6 SolQwen2-72B
GPQA Diamond94.3%40.8%
LMArena Expert14391171
SimpleQA Verified60.7%—
Vectara Hallucination Rate6.5%—
MMLU—82.4%

Multimodal Not comparable

GPT-6 Sol: 47.6 (#10), Qwen2-72B: —

BenchmarkGPT-6 SolQwen2-72B
LMArena Vision1245—
Blueprint-Bench 236.9%—
Furniture Assembly58.3%—

Multilingual GPT-6 Sol leads

GPT-6 Sol: 50.5 (#118), Qwen2-72B: 35.9 (#244)

BenchmarkGPT-6 SolQwen2-72B
LMArena Non-English13851176
LMArena Chinese14051240
LMArena French14101170
LMArena German13901151
LMArena Japanese13851111
LMArena Korean13411083
LMArena Russian14011169
LMArena Spanish13841169

Instruction Following GPT-6 Sol leads

GPT-6 Sol: 74.5 (#94), Qwen2-72B: 61.7 (#241)

BenchmarkGPT-6 SolQwen2-72B
LMArena Instruction Following14121181

Long Context GPT-6 Sol leads

GPT-6 Sol: 43.1 (#108), Qwen2-72B: 36.1 (#235)

BenchmarkGPT-6 SolQwen2-72B
LMArena Longer Query14111192

Writing & Preference GPT-6 Sol leads

GPT-6 Sol: 71.9 (#18), Qwen2-72B: 40.8 (#241)

BenchmarkGPT-6 SolQwen2-72B
LMArena Text13951203
LMArena Creative Writing13781181
LMArena Multi-Turn14121196
EQ-Bench Creative Writing2125—

Frequently asked questions

Is GPT-6 Sol better than Qwen2-72B?

GPT-6 Sol is the stronger model overall, scoring 61.8 to 30.0 on the Noometry Index.

Is GPT-6 Sol or Qwen2-72B better for coding?

GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 29.1 in the Noometry coding category.

How many benchmarks do GPT-6 Sol and Qwen2-72B share?

19 benchmarks have published results for both models. GPT-6 Sol has 45 scored results on Noometry and Qwen2-72B has 26.

Related comparisons

Go deeper