Model comparison

Gemini 4 Argon vs InternVL2-40B

Gemini 4 Argon has enough public results to be ranked (#24); InternVL2-40B does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

Gemini 4 Argon Google

56.5

Rank #24 Confirmed

InternVL2-40B Shanghai AI Lab

36.6

Unranked Sparse

Summary

  • The widest gap is in multimodal, where Gemini 4 Argon leads 46.5 to 33.7.
  • InternVL2-40B has downloadable open weights; the other is API-only.

Side by side

Gemini 4 Argon and InternVL2-40B specifications
Gemini 4 ArgonInternVL2-40B
ProviderGoogleShanghai AI Lab
Noometry Index56.536.6
Released2026-09-302024-07-08
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked211

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

Category by category

Coding Not comparable

Gemini 4 Argon: 62.0 (#9), InternVL2-40B: —

Coding benchmarks
BenchmarkGemini 4 ArgonInternVL2-40B
LMArena WebDev1678—
FrontierSWE55%—
SciCode61.8%—
LMArena Coding1550—

Agentic & Tool Use Not comparable

Gemini 4 Argon: 49.2 (#8), InternVL2-40B: —

Agentic & Tool Use benchmarks
BenchmarkGemini 4 ArgonInternVL2-40B
APEX-Agents82.2%—
Vending-Bench 213,718—

Reasoning Not comparable

Gemini 4 Argon: 44.2 (#47), InternVL2-40B: —

Reasoning benchmarks
BenchmarkGemini 4 ArgonInternVL2-40B
CritPt27.1%—
LMArena Hard Prompts1548—

Math Not comparable

Gemini 4 Argon: 73.9 (#17), InternVL2-40B: —

Math benchmarks
BenchmarkGemini 4 ArgonInternVL2-40B
ProofBench99%—
LMArena Math1536—

Knowledge Not comparable

Gemini 4 Argon: 43.9 (#89), InternVL2-40B: —

Knowledge benchmarks
BenchmarkGemini 4 ArgonInternVL2-40B
LMArena Expert1553—

Multimodal Gemini 4 Argon leads

Gemini 4 Argon: 46.5 (#14), InternVL2-40B: 33.7

Multimodal benchmarks
BenchmarkGemini 4 ArgonInternVL2-40B
Video-MME—61.2%
Blueprint-Bench 254.4%—

Multilingual Not comparable

Gemini 4 Argon: 60.3 (#1), InternVL2-40B: —

Multilingual benchmarks
BenchmarkGemini 4 ArgonInternVL2-40B
LMArena Non-English1523—
LMArena Chinese1610—
LMArena Russian1537—
LMArena Spanish1497—

Instruction Following Not comparable

Gemini 4 Argon: 80.1 (#2), InternVL2-40B: —

Instruction Following benchmarks
BenchmarkGemini 4 ArgonInternVL2-40B
LMArena Instruction Following1538—

Long Context Not comparable

Gemini 4 Argon: 47.6 (#15), InternVL2-40B: —

Long Context benchmarks
BenchmarkGemini 4 ArgonInternVL2-40B
LMArena Longer Query1549—

Writing & Preference Not comparable

Gemini 4 Argon: 71.4 (#19), InternVL2-40B: —

Writing & Preference benchmarks
BenchmarkGemini 4 ArgonInternVL2-40B
LMArena Text1534—
LMArena Creative Writing1531—
LMArena Multi-Turn1557—

Frequently asked questions

Is Gemini 4 Argon better than InternVL2-40B?

Gemini 4 Argon has enough public results to be ranked (#24); InternVL2-40B does not yet, so treat this comparison as directional.

How many benchmarks do Gemini 4 Argon and InternVL2-40B share?

0 benchmarks have published results for both models. Gemini 4 Argon has 21 scored results on Noometry and InternVL2-40B has 1.

Related comparisons

Go deeper