BenchLeader

Hermes 4 405B

Not yet ranked: too few independent results so far. Released 30 Jan 2026.

Blended price
$1.50/M
$1.00 in · $3.00 out
Output speed
35 tok/s
First answer
0.35 s
Context
131k
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Reasoning30

Reasoning-effort configurations

The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Default” means the publisher did not say which setting was used.

EffortIndexRankSpeedFirst answerChat reply costCategories
no reasoningbest35 tok/s0.35 s$0.0013Reasoning 30
thinking35 tok/s0.35 s$0.0013Reasoning 52

Benchmark results

One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

Benchmarkno reasoningthinkingSource
Kagi LLM Benchmark30.1%#12355.8%#63Kagi LLM Benchmark

Where to run it

Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.

ProviderSpeedFirst tokenInput $/MOutput $/MContextQuantisation
Nebius Token Factory35 tok/s0.35 s$1.00$3.00131kfp8

What a task costs

Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.100 per 1M. Reasoning tokens are not modelled.

WorkloadTokens in / outCostWith cachingTime
Chat reply400 / 300$0.0013$0.00108.9 s
Summarise a 30-page report12,000 / 600$0.014$0.005717.5 s
Code edit6,000 / 1,500$0.011$0.006543.2 s
Agentic coding session60,000 / 4,000$0.072$0.0321.9 min
Structured extraction2,000 / 200$0.0026$0.00136.1 s

See also

Data as of 9 Sept 2026. Compare these configurations.