Model comparison

Gemini 3.8 Flash vs InternVL2_5-78B

Gemini 3.8 Flash has enough public results to be ranked (#13); InternVL2_5-78B does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

Gemini 3.8 Flash Google

59.5

Rank #13 Confirmed

InternVL2_5-78B Shanghai AI Lab

38.6

Unranked Sparse

Summary

  • The widest gap is in multimodal, where Gemini 3.8 Flash leads 40.9 to 37.8.
  • InternVL2_5-78B has downloadable open weights; the other is API-only.

Side by side

Gemini 3.8 Flash and InternVL2_5-78B specifications
Gemini 3.8 FlashInternVL2_5-78B
ProviderGoogleShanghai AI Lab
Noometry Index59.538.6
Released2026-09-022024-12-06
WeightsProprietaryOpen
Context window1.05M—
Max output66K—
Input $ / M tokens$0.75—
Output $ / M tokens$3.75—
Results tracked461

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

Category by category

Coding Not comparable

Gemini 3.8 Flash: 56.4 (#17), InternVL2_5-78B: —

Coding benchmarks
BenchmarkGemini 3.8 FlashInternVL2_5-78B
DeepSWE73.8%—
FrontierCode41.2%—
CursorBench39.6%—
LMArena WebDev1581—
FrontierSWE19.6%—
SciCode56.6%—
LMArena Coding1512—
ALE-Bench1,270—

Agentic & Tool Use Not comparable

Gemini 3.8 Flash: 40.3 (#22), InternVL2_5-78B: —

Agentic & Tool Use benchmarks
BenchmarkGemini 3.8 FlashInternVL2_5-78B
APEX-Agents64.3%—
GDP.pdf23.4%—
Vending-Bench 25,094—

Reasoning Not comparable

Gemini 3.8 Flash: 64.7 (#13), InternVL2_5-78B: —

Reasoning benchmarks
BenchmarkGemini 3.8 FlashInternVL2_5-78B
NYT Connections (extended)97.4%—
CritPt18.3%—
Chess Puzzles61%—
LMArena Hard Prompts1506—
Mystery Game Puzzles47%—
DTBench95.7%—
LMCA52.9%—
Surface Evolver Bench76.9%—
Epoch Capabilities Index157.13—

Math Not comparable

Gemini 3.8 Flash: 65.2 (#22), InternVL2_5-78B: —

Math benchmarks
BenchmarkGemini 3.8 FlashInternVL2_5-78B
FrontierMath (Tiers 1-3)68.4%—
FrontierMath Tier 422%—
OTIS Mock AIME 2024-202598.9%—
ProofBench48%—
LMArena Math1528—

Knowledge Not comparable

Gemini 3.8 Flash: 74.9 (#2), InternVL2_5-78B: —

Knowledge benchmarks
BenchmarkGemini 3.8 FlashInternVL2_5-78B
GPQA Diamond95.4%—
Humanity's Last Exam44.5%—
SimpleQA Verified69.7%—
LMArena Expert1529—

Multimodal Gemini 3.8 Flash leads

Gemini 3.8 Flash: 40.9 (#33), InternVL2_5-78B: 37.8

Multimodal benchmarks
BenchmarkGemini 3.8 FlashInternVL2_5-78B
LMArena Vision1312—
Video-MME—72.1%
Blueprint-Bench 238.6%—
Furniture Assembly31.7%—

Multilingual Not comparable

Gemini 3.8 Flash: 57.9 (#5), InternVL2_5-78B: —

Multilingual benchmarks
BenchmarkGemini 3.8 FlashInternVL2_5-78B
LMArena Non-English1486—
LMArena Chinese1547—
LMArena French1502—
LMArena German1470—
LMArena Japanese1505—
LMArena Korean1479—
LMArena Russian1507—
LMArena Spanish1492—

Instruction Following Not comparable

Gemini 3.8 Flash: 78.2 (#11), InternVL2_5-78B: —

Instruction Following benchmarks
BenchmarkGemini 3.8 FlashInternVL2_5-78B
LMArena Instruction Following1489—

Long Context Not comparable

Gemini 3.8 Flash: 46.2 (#23), InternVL2_5-78B: —

Long Context benchmarks
BenchmarkGemini 3.8 FlashInternVL2_5-78B
LMArena Longer Query1506—

Writing & Preference Not comparable

Gemini 3.8 Flash: 72.1 (#16), InternVL2_5-78B: —

Writing & Preference benchmarks
BenchmarkGemini 3.8 FlashInternVL2_5-78B
LMArena Text1494—
LMArena Creative Writing1485—
EQ-Bench Creative Writing1748—
LMArena Multi-Turn1503—

Frequently asked questions

Is Gemini 3.8 Flash better than InternVL2_5-78B?

Gemini 3.8 Flash has enough public results to be ranked (#13); InternVL2_5-78B does not yet, so treat this comparison as directional.

How many benchmarks do Gemini 3.8 Flash and InternVL2_5-78B share?

0 benchmarks have published results for both models. Gemini 3.8 Flash has 46 scored results on Noometry and InternVL2_5-78B has 1.

Related comparisons

Go deeper