Noometry

Model comparison

Claude Opus 5 vs Hermes 4 405B

Claude Opus 5 has enough public results to be ranked (#4); Hermes 4 405B does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

Claude Opus 5 Anthropic

67.8

Rank #4 Confirmed

Hermes 4 405B Nous Research

37.6

Unranked Sparse

Summary

  • They share 1 benchmark with published results for both. Claude Opus 5 scores higher in 2 categories and Hermes 4 405B in 0 categories; 2 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Opus 5 leads 77.2 to 26.1.
  • Hermes 4 405B is cheaper at $1 / $3 per million input/output tokens, against $5 / $25 for Claude Opus 5.
  • Claude Opus 5 accepts more context: 1M tokens versus 131K.
  • Hermes 4 405B has downloadable open weights; the other is API-only.

Side by side

Claude Opus 5Hermes 4 405B
ProviderAnthropicNous Research
Noometry Index67.837.6
Released2026-07-24—
WeightsProprietaryOpen
Context window1M131K
Max output128K118K
Input $ / M tokens$5$1
Output $ / M tokens$25$3
Results tracked572

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

Category by category

Coding Not comparable

Claude Opus 5: 67.5 (#5), Hermes 4 405B: —

BenchmarkClaude Opus 5Hermes 4 405B
DeepSWE73.6%—
FrontierCode53.4%—
CursorBench46.6%—
LMArena WebDev1691—
FrontierSWE52%—
SciCode56.4%—
WeirdML91.8%—
LMArena Coding1534—
ALE-Bench2,165—

Agentic & Tool Use Not comparable

Claude Opus 5: 55.6 (#1), Hermes 4 405B: —

BenchmarkClaude Opus 5Hermes 4 405B
APEX-Agents65.8%—
OSWorld 2.031.4%—
τ²-bench Banking48.7%—
PostTrainBench35%—
BALROG63.4%—
GBAEval79.6%—
GDP.pdf24%—
Vending-Bench 211,182—

Reasoning Claude Opus 5 leads

Claude Opus 5: 77.2 (#4), Hermes 4 405B: 26.1

BenchmarkClaude Opus 5Hermes 4 405B
ARC-AGI-290.4%—
SimpleBench80.6%—
Kagi LLM Benchmark—55.8%
NYT Connections (extended)94.3%—
ARC-AGI-197.5%—
CritPt29.1%—
Chess Puzzles42%—
EBR-Bench45.7%—
LMArena Hard Prompts1526—
Mystery Game Puzzles59%—
DTBench97.9%—
LMCA64.5%—
Bench to the Future 30.12—
Epoch Capabilities Index162.78—

Math Not comparable

Claude Opus 5: 86.2 (#8), Hermes 4 405B: —

BenchmarkClaude Opus 5Hermes 4 405B
FrontierMath (Tiers 1-3)85.6%—
FrontierMath Tier 473.2%—
OTIS Mock AIME 2024-202598.9%—
ProofBench99%—
LMArena Math1531—

Knowledge Not comparable

Claude Opus 5: 66.8 (#9), Hermes 4 405B: —

BenchmarkClaude Opus 5Hermes 4 405B
GPQA Diamond93.9%—
SimpleQA Verified59.9%—
LMArena Expert1557—

Multimodal Not comparable

Claude Opus 5: 50.8 (#8), Hermes 4 405B: —

BenchmarkClaude Opus 5Hermes 4 405B
LMArena Vision1319—
Blueprint-Bench 230.4%—
Furniture Assembly60.8%—
LMArena Document1516—

Multilingual Not comparable

Claude Opus 5: 58.8 (#4), Hermes 4 405B: —

BenchmarkClaude Opus 5Hermes 4 405B
LMArena Non-English1501—
LMArena Chinese1574—
LMArena French1519—
LMArena German1524—
LMArena Japanese1516—
LMArena Korean1521—
LMArena Russian1507—
LMArena Spanish1519—

Instruction Following Not comparable

Claude Opus 5: 79.2 (#7), Hermes 4 405B: —

BenchmarkClaude Opus 5Hermes 4 405B
LMArena Instruction Following1517—

Long Context Not comparable

Claude Opus 5: 46.5 (#21), Hermes 4 405B: —

BenchmarkClaude Opus 5Hermes 4 405B
LMArena Longer Query1515—

Writing & Preference Claude Opus 5 leads

Claude Opus 5: 79.2 (#1), Hermes 4 405B: 52.9

BenchmarkClaude Opus 5Hermes 4 405B
EQ-Bench Creative Writing21331421
LMArena Text1507—
LMArena Creative Writing1491—
EQ-Bench 41385—
LMArena Multi-Turn1499—

Frequently asked questions

Is Claude Opus 5 better than Hermes 4 405B?

Claude Opus 5 has enough public results to be ranked (#4); Hermes 4 405B does not yet, so treat this comparison as directional.

Which is cheaper, Claude Opus 5 or Hermes 4 405B?

Hermes 4 405B is cheaper. It lists at $1 per million input tokens and $3 per million output tokens; Claude Opus 5 lists at $5 and $25.

Which has the bigger context window?

Claude Opus 5 does, with 1M tokens against 131K.

How many benchmarks do Claude Opus 5 and Hermes 4 405B share?

1 benchmark has published results for both models. Claude Opus 5 has 57 scored results on Noometry and Hermes 4 405B has 2.

Related comparisons

Go deeper