Noometry

Model comparison

GPT-6.1 Sol vs Qwen2-72B

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 30.0 on the Noometry Index.

Last verified . 14 shared benchmarks.

GPT-6.1 Sol OpenAI

65.6

Rank #6 Confirmed

Qwen2-72B Alibaba (Qwen)

30.0

Rank #300 Confirmed

Summary

  • They share 14 benchmarks with published results for both. GPT-6.1 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-6.1 Sol leads 93.7 to 30.2.
  • The biggest single-benchmark swing is GPQA Diamond: 95.4% for GPT-6.1 Sol and 40.8% for Qwen2-72B.
  • Qwen2-72B has downloadable open weights; the other is API-only.

Side by side

GPT-6.1 SolQwen2-72B
ProviderOpenAIAlibaba (Qwen)
Noometry Index65.630.0
Released2026-09-292024-06-07
WeightsProprietaryOpen
Context window1.05M—
Max output128K—
Input $ / M tokens$2—
Output $ / M tokens$10—
Results tracked3426

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

Category by category

Coding GPT-6.1 Sol leads

GPT-6.1 Sol: 63.2 (#8), Qwen2-72B: 29.1 (#310)

BenchmarkGPT-6.1 SolQwen2-72B
LMArena Coding14871196
DeepSWE75.2%—
FrontierCode50.2%—
LMArena WebDev1755—
SciCode55.8%—
WeirdML—11.3%
BigCodeBench Instruct—38.5%
BigCodeBench Complete—54%

Agentic & Tool Use GPT-6.1 Sol leads

GPT-6.1 Sol: 39.6 (#26), Qwen2-72B: 17.0 (#146)

BenchmarkGPT-6.1 SolQwen2-72B
APEX-Agents60%—
TheAgentCompany—1.1%
GDP.pdf32%—
METR Time Horizons—29.9%

Reasoning GPT-6.1 Sol leads

GPT-6.1 Sol: 81.9 (#2), Qwen2-72B: 23.2 (#181)

BenchmarkGPT-6.1 SolQwen2-72B
LMArena Hard Prompts14661191
Epoch Capabilities Index166.09125.28
ARC-AGI-294.2%—
NYT Connections (extended)95.5%—
ARC-AGI-198.5%—
CritPt31.7%—
Chess Puzzles61%—
EBR-Bench54.3%—
Mystery Game Puzzles80%—

Math GPT-6.1 Sol leads

GPT-6.1 Sol: 93.7 (#1), Qwen2-72B: 30.2 (#236)

BenchmarkGPT-6.1 SolQwen2-72B
LMArena Math14641235
FrontierMath (Tiers 1-3)93.7%—
FrontierMath Tier 4100%—
OTIS Mock AIME 2024-2025100%—
ProofBench99%—
MATH Level 5—39.1%

Knowledge GPT-6.1 Sol leads

GPT-6.1 Sol: 71.8 (#4), Qwen2-72B: 21.2 (#275)

BenchmarkGPT-6.1 SolQwen2-72B
GPQA Diamond95.4%40.8%
LMArena Expert15021171
SimpleQA Verified73.9%—
MMLU—82.4%

Multimodal Not comparable

GPT-6.1 Sol: 52.7 (#5), Qwen2-72B: —

BenchmarkGPT-6.1 SolQwen2-72B
LMArena Vision1288—
Furniture Assembly80%—

Multilingual GPT-6.1 Sol leads

GPT-6.1 Sol: 54.3 (#46), Qwen2-72B: 35.9 (#244)

BenchmarkGPT-6.1 SolQwen2-72B
LMArena Non-English14381176
LMArena Chinese14771240
LMArena Russian14551169
LMArena French—1170
LMArena German—1151
LMArena Japanese—1111
LMArena Korean—1083
LMArena Spanish—1169

Instruction Following GPT-6.1 Sol leads

GPT-6.1 Sol: 77.0 (#29), Qwen2-72B: 61.7 (#241)

BenchmarkGPT-6.1 SolQwen2-72B
LMArena Instruction Following14681181

Long Context GPT-6.1 Sol leads

GPT-6.1 Sol: 44.9 (#54), Qwen2-72B: 36.1 (#235)

BenchmarkGPT-6.1 SolQwen2-72B
LMArena Longer Query14651192

Writing & Preference GPT-6.1 Sol leads

GPT-6.1 Sol: 63.6 (#63), Qwen2-72B: 40.8 (#241)

BenchmarkGPT-6.1 SolQwen2-72B
LMArena Text14471203
LMArena Creative Writing14321181
LMArena Multi-Turn14491196

Frequently asked questions

Is GPT-6.1 Sol better than Qwen2-72B?

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 30.0 on the Noometry Index.

Is GPT-6.1 Sol or Qwen2-72B better for coding?

GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 29.1 in the Noometry coding category.

How many benchmarks do GPT-6.1 Sol and Qwen2-72B share?

14 benchmarks have published results for both models. GPT-6.1 Sol has 34 scored results on Noometry and Qwen2-72B has 26.

Related comparisons

Go deeper