Noometry

Model comparison

GPT-6 Sol vs Hermes 4 405B

GPT-6 Sol has enough public results to be ranked (#12); Hermes 4 405B does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

GPT-6 Sol OpenAI

61.8

Rank #12 Confirmed

Hermes 4 405B Nous Research

37.6

Unranked Sparse

Summary

  • They share 1 benchmark with published results for both. GPT-6 Sol 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 GPT-6 Sol leads 74.0 to 26.1.
  • Hermes 4 405B is cheaper at $1 / $3 per million input/output tokens, against $2 / $10 for GPT-6 Sol.
  • GPT-6 Sol accepts more context: 1.05M tokens versus 131K.
  • Hermes 4 405B has downloadable open weights; the other is API-only.

Side by side

GPT-6 SolHermes 4 405B
ProviderOpenAINous Research
Noometry Index61.837.6
Released2026-09-22—
WeightsProprietaryOpen
Context window1.05M131K
Max output128K118K
Input $ / M tokens$2$1
Output $ / M tokens$10$3
Results tracked452

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

Category by category

Coding Not comparable

GPT-6 Sol: 60.1 (#11), Hermes 4 405B: —

BenchmarkGPT-6 SolHermes 4 405B
DeepSWE68.8%—
FrontierCode49.3%—
LMArena WebDev1688—
SciCode57.6%—
LMArena Coding1447—
ALE-Bench2,462—

Agentic & Tool Use Not comparable

GPT-6 Sol: 37.2 (#36), Hermes 4 405B: —

BenchmarkGPT-6 SolHermes 4 405B
APEX-Agents54.3%—
GDP.pdf26.4%—
Vending-Bench 214,428—

Reasoning GPT-6 Sol leads

GPT-6 Sol: 74.0 (#9), Hermes 4 405B: 26.1

BenchmarkGPT-6 SolHermes 4 405B
ARC-AGI-289.6%—
Kagi LLM Benchmark—55.8%
NYT Connections (extended)90.1%—
ARC-AGI-195.5%—
CritPt30.9%—
EBR-Bench53.3%—
LMArena Hard Prompts1418—
Mystery Game Puzzles56%—
DTBench97.3%—
LMCA59.1%—
Epoch Capabilities Index162.72—

Math Not comparable

GPT-6 Sol: 87.2 (#7), Hermes 4 405B: —

BenchmarkGPT-6 SolHermes 4 405B
FrontierMath (Tiers 1-3)89.8%—
FrontierMath Tier 490%—
OTIS Mock AIME 2024-2025100%—
ProofBench83%—
LMArena Math1402—

Knowledge Not comparable

GPT-6 Sol: 64.8 (#15), Hermes 4 405B: —

BenchmarkGPT-6 SolHermes 4 405B
GPQA Diamond94.3%—
SimpleQA Verified60.7%—
Vectara Hallucination Rate6.5%—
LMArena Expert1439—

Multimodal Not comparable

GPT-6 Sol: 47.6 (#10), Hermes 4 405B: —

BenchmarkGPT-6 SolHermes 4 405B
LMArena Vision1245—
Blueprint-Bench 236.9%—
Furniture Assembly58.3%—

Multilingual Not comparable

GPT-6 Sol: 50.5 (#118), Hermes 4 405B: —

BenchmarkGPT-6 SolHermes 4 405B
LMArena Non-English1385—
LMArena Chinese1405—
LMArena French1410—
LMArena German1390—
LMArena Japanese1385—
LMArena Korean1341—
LMArena Russian1401—
LMArena Spanish1384—

Instruction Following Not comparable

GPT-6 Sol: 74.5 (#94), Hermes 4 405B: —

BenchmarkGPT-6 SolHermes 4 405B
LMArena Instruction Following1412—

Long Context Not comparable

GPT-6 Sol: 43.1 (#108), Hermes 4 405B: —

BenchmarkGPT-6 SolHermes 4 405B
LMArena Longer Query1411—

Writing & Preference GPT-6 Sol leads

GPT-6 Sol: 71.9 (#18), Hermes 4 405B: 52.9

BenchmarkGPT-6 SolHermes 4 405B
EQ-Bench Creative Writing21251421
LMArena Text1395—
LMArena Creative Writing1378—
LMArena Multi-Turn1412—

Frequently asked questions

Is GPT-6 Sol better than Hermes 4 405B?

GPT-6 Sol has enough public results to be ranked (#12); Hermes 4 405B does not yet, so treat this comparison as directional.

Which is cheaper, GPT-6 Sol or Hermes 4 405B?

Hermes 4 405B is cheaper. It lists at $1 per million input tokens and $3 per million output tokens; GPT-6 Sol lists at $2 and $10.

Which has the bigger context window?

GPT-6 Sol does, with 1.05M tokens against 131K.

How many benchmarks do GPT-6 Sol and Hermes 4 405B share?

1 benchmark has published results for both models. GPT-6 Sol has 45 scored results on Noometry and Hermes 4 405B has 2.

Related comparisons

Go deeper