Noometry

Model comparison

GPT-6 Sol vs InternVL2-40B

GPT-6 Sol has enough public results to be ranked (#46); InternVL2-40B does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

GPT-6 Sol OpenAI

49.2

Rank #46 Confirmed

InternVL2-40B Shanghai AI Lab

36.0

Unranked Sparse

Summary

  • The widest gap is in multimodal, where GPT-6 Sol leads 47.6 to 33.0.
  • InternVL2-40B has downloadable open weights; the other is API-only.

Side by side

GPT-6 SolInternVL2-40B
ProviderOpenAIShanghai AI Lab
Noometry Index49.236.0
Released2026-09-222024-07-08
WeightsProprietaryOpen
Context window1.05M—
Max output128K—
Input $ / M tokens$2—
Output $ / M tokens$10—
Results tracked221

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

Category by category

Coding Not comparable

GPT-6 Sol: 59.6 (#11), InternVL2-40B: —

BenchmarkGPT-6 SolInternVL2-40B
DeepSWE68.8%—
FrontierCode49.3%—
LMArena WebDev1692—
LMArena Coding1453—

Agentic & Tool Use Not comparable

GPT-6 Sol: 33.5 (#49), InternVL2-40B: —

BenchmarkGPT-6 SolInternVL2-40B
GDP.pdf28%—

Reasoning Not comparable

GPT-6 Sol: 49.3 (#34), InternVL2-40B: —

BenchmarkGPT-6 SolInternVL2-40B
NYT Connections (extended)90.1%—
EBR-Bench53.3%—
LMArena Hard Prompts1420—

Math Not comparable

GPT-6 Sol: 35.8 (#135), InternVL2-40B: —

BenchmarkGPT-6 SolInternVL2-40B
LMArena Math1404—

Knowledge Not comparable

GPT-6 Sol: 43.0 (#87), InternVL2-40B: —

BenchmarkGPT-6 SolInternVL2-40B
Vectara Hallucination Rate6.5%—
LMArena Expert1449—

Multimodal GPT-6 Sol leads

GPT-6 Sol: 47.6 (#9), InternVL2-40B: 33.0

BenchmarkGPT-6 SolInternVL2-40B
Video-MME—61.2%
Furniture Assembly58.3%—

Multilingual Not comparable

GPT-6 Sol: 51.0 (#113), InternVL2-40B: —

BenchmarkGPT-6 SolInternVL2-40B
LMArena Non-English1389—
LMArena Chinese1416—
LMArena Russian1407—
LMArena Spanish1377—

Instruction Following Not comparable

GPT-6 Sol: 74.4 (#97), InternVL2-40B: —

BenchmarkGPT-6 SolInternVL2-40B
LMArena Instruction Following1406—

Long Context Not comparable

GPT-6 Sol: 43.2 (#100), InternVL2-40B: —

BenchmarkGPT-6 SolInternVL2-40B
LMArena Longer Query1415—

Writing & Preference Not comparable

GPT-6 Sol: 72.3 (#15), InternVL2-40B: —

BenchmarkGPT-6 SolInternVL2-40B
LMArena Text1396—
LMArena Creative Writing1392—
EQ-Bench Creative Writing2125—
LMArena Multi-Turn1405—

Frequently asked questions

Is GPT-6 Sol better than InternVL2-40B?

GPT-6 Sol has enough public results to be ranked (#46); InternVL2-40B does not yet, so treat this comparison as directional.

How many benchmarks do GPT-6 Sol and InternVL2-40B share?

0 benchmarks have published results for both models. GPT-6 Sol has 22 scored results on Noometry and InternVL2-40B has 1.

Related comparisons

Go deeper