Noometry

Model comparison

GPT-6.1 Sol vs WizardLM-2 8x22B

GPT-6.1 Sol has enough public results to be ranked (#6); WizardLM-2 8x22B does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

GPT-6.1 Sol OpenAI

65.6

Rank #6 Confirmed

WizardLM-2 8x22B Microsoft

31.4

Unranked Sparse

Summary

  • They share 1 benchmark with published results for both. GPT-6.1 Sol scores higher in 2 categories and WizardLM-2 8x22B in 0 categories; 2 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6.1 Sol leads 93.7 to 28.9.
  • The biggest single-benchmark swing is GPQA Diamond: 95.4% for GPT-6.1 Sol and 43.4% for WizardLM-2 8x22B.
  • WizardLM-2 8x22B is cheaper at $0.62 / $0.62 per million input/output tokens, against $2 / $10 for GPT-6.1 Sol.
  • GPT-6.1 Sol accepts more context: 1.05M tokens versus 66K.
  • WizardLM-2 8x22B has downloadable open weights; the other is API-only.

Side by side

GPT-6.1 SolWizardLM-2 8x22B
ProviderOpenAIMicrosoft
Noometry Index65.631.4
Released2026-09-292024-04-15
WeightsProprietaryOpen
Context window1.05M66K
Max output128K8K
Input $ / M tokens$2$0.62
Output $ / M tokens$10$0.62
Results tracked342

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

Category by category

Coding Not comparable

GPT-6.1 Sol: 63.2 (#8), WizardLM-2 8x22B: —

BenchmarkGPT-6.1 SolWizardLM-2 8x22B
DeepSWE75.2%—
FrontierCode50.2%—
LMArena WebDev1755—
SciCode55.8%—
LMArena Coding1487—

Agentic & Tool Use Not comparable

GPT-6.1 Sol: 39.6 (#26), WizardLM-2 8x22B: —

BenchmarkGPT-6.1 SolWizardLM-2 8x22B
APEX-Agents60%—
GDP.pdf32%—

Reasoning Not comparable

GPT-6.1 Sol: 81.9 (#2), WizardLM-2 8x22B: —

BenchmarkGPT-6.1 SolWizardLM-2 8x22B
ARC-AGI-294.2%—
NYT Connections (extended)95.5%—
ARC-AGI-198.5%—
CritPt31.7%—
Chess Puzzles61%—
EBR-Bench54.3%—
LMArena Hard Prompts1466—
Mystery Game Puzzles80%—
Epoch Capabilities Index166.09—

Math GPT-6.1 Sol leads

GPT-6.1 Sol: 93.7 (#1), WizardLM-2 8x22B: 28.9

BenchmarkGPT-6.1 SolWizardLM-2 8x22B
FrontierMath (Tiers 1-3)93.7%—
FrontierMath Tier 4100%—
OTIS Mock AIME 2024-2025100%—
ProofBench99%—
LMArena Math1464—
MATH Level 5—25.7%

Knowledge GPT-6.1 Sol leads

GPT-6.1 Sol: 71.8 (#4), WizardLM-2 8x22B: 23.3

BenchmarkGPT-6.1 SolWizardLM-2 8x22B
GPQA Diamond95.4%43.4%
SimpleQA Verified73.9%—
LMArena Expert1502—

Multimodal Not comparable

GPT-6.1 Sol: 52.7 (#5), WizardLM-2 8x22B: —

BenchmarkGPT-6.1 SolWizardLM-2 8x22B
LMArena Vision1288—
Furniture Assembly80%—

Multilingual Not comparable

GPT-6.1 Sol: 54.3 (#46), WizardLM-2 8x22B: —

BenchmarkGPT-6.1 SolWizardLM-2 8x22B
LMArena Non-English1438—
LMArena Chinese1477—
LMArena Russian1455—

Instruction Following Not comparable

GPT-6.1 Sol: 77.0 (#29), WizardLM-2 8x22B: —

BenchmarkGPT-6.1 SolWizardLM-2 8x22B
LMArena Instruction Following1468—

Long Context Not comparable

GPT-6.1 Sol: 44.9 (#54), WizardLM-2 8x22B: —

BenchmarkGPT-6.1 SolWizardLM-2 8x22B
LMArena Longer Query1465—

Writing & Preference Not comparable

GPT-6.1 Sol: 63.6 (#63), WizardLM-2 8x22B: —

BenchmarkGPT-6.1 SolWizardLM-2 8x22B
LMArena Text1447—
LMArena Creative Writing1432—
LMArena Multi-Turn1449—

Frequently asked questions

Is GPT-6.1 Sol better than WizardLM-2 8x22B?

GPT-6.1 Sol has enough public results to be ranked (#6); WizardLM-2 8x22B does not yet, so treat this comparison as directional.

Which is cheaper, GPT-6.1 Sol or WizardLM-2 8x22B?

WizardLM-2 8x22B is cheaper. It lists at $0.62 per million input tokens and $0.62 per million output tokens; GPT-6.1 Sol lists at $2 and $10.

Which has the bigger context window?

GPT-6.1 Sol does, with 1.05M tokens against 66K.

How many benchmarks do GPT-6.1 Sol and WizardLM-2 8x22B share?

1 benchmark has published results for both models. GPT-6.1 Sol has 34 scored results on Noometry and WizardLM-2 8x22B has 2.

Related comparisons

Go deeper