Noometry

Model comparison

Gemini 3.5 Flash vs Hermes 4 405B

Gemini 3.5 Flash has enough public results to be ranked (#29); Hermes 4 405B does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

Gemini 3.5 Flash Google

54.1

Rank #29 Confirmed

Hermes 4 405B Nous Research

37.1

Unranked Sparse

Summary

  • The widest gap is in reasoning, where Gemini 3.5 Flash leads 62.7 to 25.3.
  • Hermes 4 405B is cheaper at $1 / $3 per million input/output tokens, against $1.50 / $9 for Gemini 3.5 Flash.
  • Gemini 3.5 Flash accepts more context: 1.05M tokens versus 131K.
  • Hermes 4 405B has downloadable open weights; the other is API-only.

Side by side

Gemini 3.5 FlashHermes 4 405B
ProviderGoogleNous Research
Noometry Index54.137.1
Released2026-05-19—
WeightsProprietaryOpen
Context window1.05M131K
Max output66K118K
Input $ / M tokens$1.50$1
Output $ / M tokens$9$3
Results tracked542

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

Category by category

Coding Not comparable

Gemini 3.5 Flash: 49.1 (#46), Hermes 4 405B: —

BenchmarkGemini 3.5 FlashHermes 4 405B
SWE-bench Verified79.3%—
DeepSWE37.4%—
LMArena WebDev1499—
SciCode53.1%—
WeirdML62.6%—
LMArena Coding1492—
ALE-Bench911.02—

Agentic & Tool Use Not comparable

Gemini 3.5 Flash: 24.8 (#107), Hermes 4 405B: —

BenchmarkGemini 3.5 FlashHermes 4 405B
APEX-Agents27.5%—
GBAEval6.7%—
GDP.pdf14%—
Vending-Bench 25,396—

Reasoning Gemini 3.5 Flash leads

Gemini 3.5 Flash: 62.7 (#16), Hermes 4 405B: 25.3

BenchmarkGemini 3.5 FlashHermes 4 405B
ARC-AGI-272.1%—
SimpleBench76.7%—
Kagi LLM Benchmark—55.8%
NYT Connections (extended)92.6%—
ARC-AGI-192.5%—
CritPt13.1%—
Chess Puzzles50%—
EnigmaEval25.4%—
EBR-Bench4.8%—
LMArena Hard Prompts1488—
Mystery Game Puzzles32%—
DTBench94.7%—
LMCA47.1%—
Surface Evolver Bench58.1%—
Epoch Capabilities Index154.55—
ForecastBench59—

Math Not comparable

Gemini 3.5 Flash: 60.5 (#30), Hermes 4 405B: —

BenchmarkGemini 3.5 FlashHermes 4 405B
FrontierMath (Tiers 1-3)62.8%—
FrontierMath Tier 426.8%—
MathArena Final-Answer Competitions76.3%—
OTIS Mock AIME 2024-202595.6%—
ProofBench31%—
LMArena Math1502—
FrontierMath (Feb 2025 set)39%—
FrontierMath Tier 4 (v1)14.6%—

Knowledge Not comparable

Gemini 3.5 Flash: 66.3 (#10), Hermes 4 405B: —

BenchmarkGemini 3.5 FlashHermes 4 405B
GPQA Diamond92.8%—
SimpleQA Verified66.2%—
LMArena Expert1493—

Multimodal Not comparable

Gemini 3.5 Flash: 45.7 (#13), Hermes 4 405B: —

BenchmarkGemini 3.5 FlashHermes 4 405B
LMArena Vision1311—
Blueprint-Bench 233.6%—
LMArena Document1463—

Multilingual Not comparable

Gemini 3.5 Flash: 57.1 (#12), Hermes 4 405B: —

BenchmarkGemini 3.5 FlashHermes 4 405B
LMArena Non-English1475—
LMArena Chinese1525—
LMArena French1490—
LMArena German1500—
LMArena Japanese1481—
LMArena Korean1453—
LMArena Russian1491—
LMArena Spanish1478—

Instruction Following Not comparable

Gemini 3.5 Flash: 77.2 (#29), Hermes 4 405B: —

BenchmarkGemini 3.5 FlashHermes 4 405B
LMArena Instruction Following1466—

Long Context Not comparable

Gemini 3.5 Flash: 45.3 (#39), Hermes 4 405B: —

BenchmarkGemini 3.5 FlashHermes 4 405B
LMArena Longer Query1481—

Writing & Preference Gemini 3.5 Flash leads

Gemini 3.5 Flash: 65.5 (#46), Hermes 4 405B: 53.0

BenchmarkGemini 3.5 FlashHermes 4 405B
LMArena Text1481—
LMArena Creative Writing1467—
EQ-Bench Creative Writing—1421
EQ-Bench 41087—
LMArena Multi-Turn1482—

Frequently asked questions

Is Gemini 3.5 Flash better than Hermes 4 405B?

Gemini 3.5 Flash has enough public results to be ranked (#29); Hermes 4 405B does not yet, so treat this comparison as directional.

Which is cheaper, Gemini 3.5 Flash or Hermes 4 405B?

Hermes 4 405B is cheaper. It lists at $1 per million input tokens and $3 per million output tokens; Gemini 3.5 Flash lists at $1.50 and $9.

Which has the bigger context window?

Gemini 3.5 Flash does, with 1.05M tokens against 131K.

How many benchmarks do Gemini 3.5 Flash and Hermes 4 405B share?

0 benchmarks have published results for both models. Gemini 3.5 Flash has 54 scored results on Noometry and Hermes 4 405B has 2.

Related comparisons

Go deeper