NOUMENOpen app
NOUMEN

Google · Open weights

Gemma 4 26B A4B Chimera X Heretic

Added Oct 8, 2026Open weights

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

Chimera X Heretic is a Gemma 4 26B A4B multimodal mixture-of-experts fine-tune for creative writing, expressive dialogue, and roleplay.

  • Reasoning
  • Tools
  • Vision
Input
Text, Images
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.12
Output
$0.38
Cache read
$0.06

Reference prices as published by the model provider. API example

Specifications

Context window
262.1K
Max output
32.8K
Average output (7 days)
315 tokens
Longer than 34% of 473 models

Side by side

Gemma 4 26B A4B Chimera X Heretic compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Gemma 4 26B A4B Chimera X HereticGoogleThis modelGLM 4.5 AirZ.aiRemove
ProviderGoogleZ.ai
Discovery tierOpen weightsOpen weights
AddedOct 8, 2026Apr 15, 2025
Limits
Context window262.14KBest128K
Max output32.77K98.3KBest
Average output315 tokens59 tokens
Pricing, USD per 1M tokens
Input$0.12Best$0.13
Output$0.38Best$0.85
Cache read$0.06$0.025Best
Performance
Throughput72.7 tok/s74.0 tok/sBest
Time to first token2.2 s1.9 sBest
Request success (24h)97.7%100.0%Best
Benchmark indexes
Intelligence Index—11.1
Math Index—80.7
Capabilities
ReasoningYesNo
ToolsYesYes
VisionYesNo
Structured outputNoYes
Reasoning effort——

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

  • Gemma 4 26B A4B Chimera X Heretic
  • GLM 4.5 Air

Intelligence Index

  • Gemma 4 26B A4B Chimera X Heretic—
  • GLM 4.5 Air11.1
3.8Catalog models by score55.1

Indexes

  • Math Index

    Composite of the math evaluations

    • Gemma 4 26B A4B Chimera X Heretic: —
    • GLM 4.5 Air: 80.7

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • Gemma 4 26B A4B Chimera X Heretic: —
    • GLM 4.5 Air: 46.7%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Gemma 4 26B A4B Chimera X Heretic: —
    • GLM 4.5 Air: 7.0%

  • GPQA Diamond

    Graduate-level science questions

    • Gemma 4 26B A4B Chimera X Heretic: —
    • GLM 4.5 Air: 73.3%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Gemma 4 26B A4B Chimera X Heretic: —
    • GLM 4.5 Air: 81.5%

  • IFBench

    Following precise output instructions

    • Gemma 4 26B A4B Chimera X Heretic: —
    • GLM 4.5 Air: 37.6%

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • Gemma 4 26B A4B Chimera X Heretic: —
    • GLM 4.5 Air: 68.4%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Gemma 4 26B A4B Chimera X Heretic: —
    • GLM 4.5 Air: 80.7%

  • AIME

    Competition mathematics

    • Gemma 4 26B A4B Chimera X Heretic: —
    • GLM 4.5 Air: 67.3%

  • MATH-500

    Competition math problems

    • Gemma 4 26B A4B Chimera X Heretic: —
    • GLM 4.5 Air: 96.5%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Gemma 4 26B A4B Chimera X Heretic: —
    • GLM 4.5 Air: 20.5%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Gemma 4 26B A4B Chimera X Heretic: —
    • GLM 4.5 Air: 46.5%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Gemma 4 26B A4B Chimera X Heretic: —
    • GLM 4.5 Air: 46.7%

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Throughput
72.7 tok/s
Faster than 53% of 260 models
Time to first token
2.2 s
Quicker than 70% of 260 models
Prompt cache hits
24.4%
About $0.11 per 1M input tokens with caching
Request success (24h)
97.7%
Reliable

Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.

Hourly request success · last 72 hoursLowest hour 72.2%
  • Healthy (98% or more)
  • Degraded (90–98%)
  • Down (under 90%)
  • No requests

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemma-4-26b-a4b-it-chimeraxheretic",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="gemma-4-26b-a4b-it-chimeraxheretic",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Google

Other Google models, starting with the same family.