ZMIME
Comparison · 3 models · Updated Nov 18, 2026

GPT-6 Cyber vs Claude Opus 4.8 vs Inkling 2 Small

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

Price in rating: Included · Exclude price

  1. OpenAI

    GPT-6 Cyber

    Released Nov 5, 2026New

    62/100
    • ECI—
    • Price—
    • Context1.05M
  2. Anthropic

    Claude Opus 4.8

    Released May 28, 2026

    74/100
    • ECI159.9
    • Price$5.00 / $25.00
    • Context1M
  3. Thinking Machines

    Inkling 2 Small

    Released Nov 5, 2026New

    62/100
    • ECI—
    • Price$0.30 / $1.00
    • Context1.05M
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Claude Opus 4.8 74/100, GPT-6 Cyber 62/100, Inkling 2 Small 62/100) compare the available specifications and price. 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 priceInkling 2 SmallInkling 2 Small $0.475 · Claude Opus 4.8 $10.00 per 1M tokens (3:1 blend) · GPT-6 Cyber unpriced
  • Longest contextGPT-6 Cyber and Inkling 2 SmallGPT-6 Cyber 1,050,000 · Inkling 2 Small 1,048,576 · Claude Opus 4.8 1,000,000 tokens
  • Widest inputsClaude Opus 4.8GPT-6 Cyber: Text, Images · Claude Opus 4.8: Text, Images, PDFs · Inkling 2 Small: Text, Images
  • Self-hostingInkling 2 SmallPublishes downloadable weights (Apache-2.0)
How the score is built
MeasureWeightGPT-6 CyberClaude Opus 4.8Inkling 2 Small
Inputs & features60%608060
Context window40%656465
Specs & price only100%62/10074/10062/100

Left out because at least one model lacks the data: capability and price. 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.

GPT-6 Cyber vs Claude Opus 4.8 vs Inkling 2 Small specifications side by side
SpecificationGPT-6 CyberOpenAIClaude Opus 4.8AnthropicInkling 2 SmallThinking Machines
Capability
Capabilities Index (ECI)—159.9—
ECI rank—#22 of 158—
GPQA DiamondGraduate-level science questions—91.0%—
FrontierMath Tiers 1–3Research-level mathematics—80.0%—
OTIS Mock AIME 2024–2025Competition mathematics—98.3%—
SimpleQA VerifiedShort factual questions—53.0%—
Price per million tokens
Input—$5.00$0.30 (best)
Output—$25.00$1.00 (best)
Cached input—$0.50—
Blended (3:1)—$10.00$0.475 (best)
Long-context rate—Same rateSame rate
Price source—Official Anthropic APIMedian of 12 providers
Limits
Context window1,050,000 tokens (best)1,000,000 tokens1,048,576 tokens
Max output128,000 tokens128,000 tokens131,072 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsNoYesNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesYeslow · medium · high · xhigh · maxYes
Tool callingYesYesYes
Structured outputNoYesNo
Availability
WeightsProprietaryProprietaryOpenApache-2.0
API model ID—claude-opus-4-8—
API providers—57 (best)13
ReleasedNov 5, 2026May 28, 2026Nov 5, 2026
Knowledge cutoff—Jan 2026—
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.

  • GPT-6 Cyber—
  • Claude Opus 4.8$100.00
  • Inkling 2 Small$5.00
04 — Questions

Which should you choose?

Which is better: GPT-6 Cyber, Claude Opus 4.8 or Inkling 2 Small?

There is not enough shared capability evidence to name an overall winner. The scores (Claude Opus 4.8 74/100, GPT-6 Cyber 62/100, Inkling 2 Small 62/100) compare the available specifications and price. 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, GPT-6 Cyber, Claude Opus 4.8 or Inkling 2 Small?

Inkling 2 Small is cheaper at $0.30 input / $1.00 output per million tokens (median across 12 API providers). Claude Opus 4.8 costs $5.00 input / $25.00 output per million tokens (official Anthropic API price). At a typical mix of three input tokens to one output token, that is $0.475 per million tokens for Inkling 2 Small versus $10.00 for Claude Opus 4.8 (21× as much). GPT-6 Cyber has no published per-token price.

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. GPT-6 Cyber has not been scored yet, Claude Opus 4.8 has an ECI of 159.9 and Inkling 2 Small has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for GPT-6 Cyber, Claude Opus 4.8 and Inkling 2 Small 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?

GPT-6 Cyber and Inkling 2 Small have the largest context windows (1,050,000 and 1,048,576 tokens), against 1,000,000 for Claude Opus 4.8. Maximum output per response: GPT-6 Cyber up to 128,000, Claude Opus 4.8 up to 128,000, Inkling 2 Small up to 131,072 tokens.

Which can read images, PDFs, audio or video?

GPT-6 Cyber accepts text and images; Claude Opus 4.8 accepts text, images and PDFs; Inkling 2 Small accepts text and images. Claude Opus 4.8 handles the widest range of inputs.

Are any of these open source?

Inkling 2 Small publishes its weights (Apache-2.0) and can be self-hosted; GPT-6 Cyber and Claude Opus 4.8 is proprietary.

Which is newer?

GPT-6 Cyber is the newest, released Nov 5, 2026. Inkling 2 Small came out Nov 5, 2026; Claude Opus 4.8 came out May 28, 2026. Knowledge cutoff: Claude Opus 4.8 Jan 2026.

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.