ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Claude Fable 5.2 vs GPT-6.2 Astra vs MiMo-V2.6-Flash

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

Price in rating: Excluded · Include price

  1. Anthropic

    Claude Fable 5.2

    Released Nov 9, 2026New

    74/100
    • ECI173.5
    • Price$8.00 / $40.00
    • Context1M
  2. OpenAI

    GPT-6.2 Astra

    Released Nov 17, 2026New

    74/100
    • ECI174.2
    • Price$8.00 / $40.00
    • Context1.05M
  3. Xiaomi

    MiMo-V2.6-Flash

    Released Sep 22, 2026New

    80/100
    • ECI—
    • Price$0.14 / $0.28
    • Context1.05M
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (MiMo-V2.6-Flash 80/100, GPT-6.2 Astra 74/100, Claude Fable 5.2 74/100) 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 priceMiMo-V2.6-FlashMiMo-V2.6-Flash $0.175 · Claude Fable 5.2 $16.00 · GPT-6.2 Astra $16.00 per 1M tokens (3:1 blend)
  • Longest contextGPT-6.2 Astra and MiMo-V2.6-FlashGPT-6.2 Astra 1,050,000 · MiMo-V2.6-Flash 1,048,576 · Claude Fable 5.2 1,000,000 tokens
  • Widest inputsMiMo-V2.6-FlashClaude Fable 5.2: Text, Images, PDFs · GPT-6.2 Astra: Text, Images, PDFs · MiMo-V2.6-Flash: Text, Images, Audio, Video
  • Self-hostingMiMo-V2.6-FlashPublishes downloadable weights
How the score is built
MeasureWeightClaude Fable 5.2GPT-6.2 AstraMiMo-V2.6-Flash
Inputs & features60%808090
Context window40%646565
Specs only100%74/10074/10080/100

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.

Claude Fable 5.2 vs GPT-6.2 Astra vs MiMo-V2.6-Flash specifications side by side
SpecificationClaude Fable 5.2AnthropicGPT-6.2 AstraOpenAIMiMo-V2.6-FlashXiaomi
Capability
Capabilities Index (ECI)173.5174.2 (best)—
ECI rank#2 of 158#1 of 158 (best)—
GPQA DiamondGraduate-level science questions96.0%96.8% (best)—
FrontierMath Tiers 1–3Research-level mathematics95.1% (best)92.6%—
OTIS Mock AIME 2024–2025Competition mathematics99.7%100% (best)—
SimpleQA VerifiedShort factual questions94.0% (best)78.5%—
Price per million tokens
Input$8.00$8.00$0.14 (best)
Output$40.00$40.00$0.28 (best)
Cached input$0.20$0.40$0.0028 (best)
Blended (3:1)$16.00$16.00$0.175 (best)
Long-context rateSame rateOver 272K: $16.00 / $60.00Same rate
Price sourceOfficial Anthropic APIOfficial OpenAI APIOfficial Xiaomi API
Limits
Context window1,000,000 tokens1,050,000 tokens (best)1,048,576 tokens
Max output128,000 tokens128,000 tokens131,072 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsYesYesNo
AudioNoNoYes
VideoNoNoYes
ReasoningYeslow · medium · high · xhigh · maxYeslow · medium · high · xhigh · maxYes
Tool callingYesYesYes
Structured outputYesYesYes
Availability
WeightsProprietaryProprietaryOpen
API model IDclaude-fable-5-2gpt-6.2-astramimo-v2.6-flash
API providers251226 (best)
ReleasedNov 9, 2026Nov 17, 2026Sep 22, 2026
Knowledge cutoffJun 2026May 18, 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.

  • Claude Fable 5.2$160.00
  • GPT-6.2 Astra$160.00
  • MiMo-V2.6-Flash$1.96
04 — Questions

Which should you choose?

Which is better: Claude Fable 5.2, GPT-6.2 Astra or MiMo-V2.6-Flash?

There is not enough shared capability evidence to name an overall winner. The scores (MiMo-V2.6-Flash 80/100, GPT-6.2 Astra 74/100, Claude Fable 5.2 74/100) 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, Claude Fable 5.2, GPT-6.2 Astra or MiMo-V2.6-Flash?

MiMo-V2.6-Flash is cheaper at $0.14 input / $0.28 output per million tokens (official Xiaomi API price). Claude Fable 5.2 costs $8.00 input / $40.00 output per million tokens (official Anthropic API price); GPT-6.2 Astra costs $8.00 input / $40.00 output per million tokens (official OpenAI API price). At a typical mix of three input tokens to one output token, that is $0.175 per million tokens for MiMo-V2.6-Flash versus $16.00 for Claude Fable 5.2 (91× as much) and $16.00 for GPT-6.2 Astra (91× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Claude Fable 5.2 has an ECI of 173.5, GPT-6.2 Astra has an ECI of 174.2 and MiMo-V2.6-Flash has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Claude Fable 5.2, GPT-6.2 Astra and MiMo-V2.6-Flash 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-6.2 Astra and MiMo-V2.6-Flash have the largest context windows (1,050,000 and 1,048,576 tokens), against 1,000,000 for Claude Fable 5.2. Maximum output per response: Claude Fable 5.2 up to 128,000, GPT-6.2 Astra up to 128,000, MiMo-V2.6-Flash up to 131,072 tokens.

Which can read images, PDFs, audio or video?

Claude Fable 5.2 accepts text, images and PDFs; GPT-6.2 Astra accepts text, images and PDFs; MiMo-V2.6-Flash accepts text, images, audio and video. MiMo-V2.6-Flash handles the widest range of inputs.

Are any of these open source?

MiMo-V2.6-Flash publishes its weights and can be self-hosted; Claude Fable 5.2 and GPT-6.2 Astra is proprietary.

Which is newer?

GPT-6.2 Astra is the newest, released Nov 17, 2026. Claude Fable 5.2 came out Nov 9, 2026; MiMo-V2.6-Flash came out Sep 22, 2026. Knowledge cutoff: Claude Fable 5.2 Jun 2026, GPT-6.2 Astra May 18, 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.