ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Gemini 2.5 Flash Preview 05-20 vs Hermes 4 405B vs Kimi K2 Instruct

No independent capability benchmark covers every model here yet. The score uses inputs & features and context window.

Price in rating: Excluded · Include price

  1. Google

    Gemini 2.5 Flash Preview 05-20

    Released May 20, 2025

    80/100
    • ECI141.6
    • Price$0.142 / $3.33
    • Context1.05M
  2. Nous Research

    Hermes 4 405B

    Released Aug 26, 2025

    34/100
    • ECI—
    • Price$1.00 / $3.00
    • Context131K
  3. Moonshot AI

    Kimi K2 Instruct

    Released Jul 11, 2025

    28/100
    • ECI141.3
    • Price$0.57 / $2.30
    • Context131K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Gemini 2.5 Flash Preview 05-20 80/100, Hermes 4 405B 34/100, Kimi K2 Instruct 28/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

  • CapabilityNot enough dataNo independent benchmark covers every model here yet
  • Lowest priceGemini 2.5 Flash Preview 05-20Gemini 2.5 Flash Preview 05-20 $0.938 · Kimi K2 Instruct $1.00 · Hermes 4 405B $1.50 per 1M tokens (3:1 blend)
  • Longest contextGemini 2.5 Flash Preview 05-20Gemini 2.5 Flash Preview 05-20 1,048,576 · Hermes 4 405B 131,072 · Kimi K2 Instruct 131,072 tokens
  • Widest inputsGemini 2.5 Flash Preview 05-20Gemini 2.5 Flash Preview 05-20: Text, Images, PDFs, Audio, Video · Hermes 4 405B: Text · Kimi K2 Instruct: Text
  • Self-hostingHermes 4 405B and Kimi K2 InstructPublishes downloadable weights (Modified MIT)
How the score is built
MeasureWeightGemini 2.5 Flash Preview 05-20Hermes 4 405BKimi K2 Instruct
Inputs & features60%903525
Context window40%653232
Specs only100%80/10034/10028/100

Left out because at least one model lacks the data: capability. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

Gemini 2.5 Flash Preview 05-20 vs Hermes 4 405B vs Kimi K2 Instruct specifications side by side
SpecificationGemini 2.5 Flash Preview 05-20GoogleHermes 4 405BNous ResearchKimi K2 InstructMoonshot AI
Capability
Capabilities Index (ECI)141.6 (best)—141.3
ECI rank#106 of 158 (best)—#108 of 158
OTIS Mock AIME 2024–2025Competition mathematics70.8%——
Price per million tokens
Input$0.142 (best)$1.00$0.57
Output$3.33$3.00$2.30 (best)
Cached input———
Blended (3:1)$0.938 (best)$1.50$1.00
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 1 providersMedian of 4 providersMedian of 11 providers
Limits
Context window1,048,576 tokens (best)131,072 tokens131,072 tokens
Max output65,536 tokens117,964 tokens (best)32,768 tokens
Inputs and features
TextYesYesYes
ImagesYesNoNo
PDFsYesNoNo
AudioYesNoNo
VideoYesNoNo
ReasoningYesYesNo
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsProprietaryOpenOpenModified MIT
API model ID———
API providers1411 (best)
ReleasedMay 20, 2025Aug 26, 2025Jul 11, 2025
Knowledge cutoffJan 2025Aug 31, 2024—
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • Gemini 2.5 Flash Preview 05-20$8.07
  • Hermes 4 405B$16.00
  • Kimi K2 Instruct$10.30
04 — Questions

Which should you choose?

Which is better: Gemini 2.5 Flash Preview 05-20, Hermes 4 405B or Kimi K2 Instruct?

There is not enough shared capability evidence to name an overall winner. The scores (Gemini 2.5 Flash Preview 05-20 80/100, Hermes 4 405B 34/100, Kimi K2 Instruct 28/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Gemini 2.5 Flash Preview 05-20, Hermes 4 405B or Kimi K2 Instruct?

Gemini 2.5 Flash Preview 05-20 is cheaper at $0.142 input / $3.33 output per million tokens (median across 1 API provider). Kimi K2 Instruct costs $0.57 input / $2.30 output per million tokens (median across 11 API providers); Hermes 4 405B costs $1.00 input / $3.00 output per million tokens (median across 4 API providers). At a typical mix of three input tokens to one output token, that is $0.938 per million tokens for Gemini 2.5 Flash Preview 05-20 versus $1.00 for Kimi K2 Instruct (1.1× as much) and $1.50 for Hermes 4 405B (1.6× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Gemini 2.5 Flash Preview 05-20 has an ECI of 141.6, Hermes 4 405B has not been scored yet and Kimi K2 Instruct has an ECI of 141.3.

Which is better for coding?

There are no published SWE-bench Verified results for Gemini 2.5 Flash Preview 05-20, Hermes 4 405B and Kimi K2 Instruct yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.

Which has the bigger context window?

Gemini 2.5 Flash Preview 05-20 has the largest context window at 1,048,576 tokens, against 131,072 for Hermes 4 405B and 131,072 for Kimi K2 Instruct. Maximum output per response: Gemini 2.5 Flash Preview 05-20 up to 65,536, Hermes 4 405B up to 117,964, Kimi K2 Instruct up to 32,768 tokens.

Which can read images, PDFs, audio or video?

Gemini 2.5 Flash Preview 05-20 accepts text, images, PDFs, audio and video; Hermes 4 405B accepts text; Kimi K2 Instruct accepts text. Gemini 2.5 Flash Preview 05-20 handles the widest range of inputs.

Are any of these open source?

Hermes 4 405B and Kimi K2 Instruct publishes its weights (Modified MIT) and can be self-hosted; Gemini 2.5 Flash Preview 05-20 is proprietary.

Which is newer?

Hermes 4 405B is the newest, released Aug 26, 2025. Kimi K2 Instruct came out Jul 11, 2025; Gemini 2.5 Flash Preview 05-20 came out May 20, 2025. Knowledge cutoff: Gemini 2.5 Flash Preview 05-20 Jan 2025, Hermes 4 405B Aug 31, 2024.

How do you decide the winner?

This rating uses inputs & features (60%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (40%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 18, 2026.