ZMIME
Comparison · 3 models · Updated Nov 22, 2026

Claude Fable 5 vs Gemini 4 Neon vs GPT-5.6 Sol

Gemini 4 Neon comes out ahead, 70 to 64 and 62 on our weighted score, and it is the cheaper option too.Gemini 4 Neon comes out ahead, 89 to 83 and 83 on our weighted score, and it is the cheaper option too.

  1. Anthropic

    Claude Fable 5

    Released Jun 9, 2026

    62/100
    • ECI164.2
    • Price$10.00 / $50.00
    • Context1M
  2. Our pick

    Google

    Gemini 4 Neon

    Released Nov 18, 2026

    70/100
    • ECI—
    • Price$3.00 / $15.00
    • Context1.05M
  3. OpenAI

    GPT-5.6 Sol

    Released Jul 9, 2026

    64/100
    • ECI163.0
    • Price$4.00 / $20.00
    • Context1.05M
  4. Anthropic

    Claude Fable 5

    Released Jun 9, 2026

    83/100
    • ECI164.2
    • Price$10.00 / $50.00
    • Context1M
  5. Our pick

    Google

    Gemini 4 Neon

    Released Nov 18, 2026

    89/100
    • ECI—
    • Price$3.00 / $15.00
    • Context1.05M
  6. OpenAI

    GPT-5.6 Sol

    Released Jul 9, 2026

    83/100
    • ECI163.0
    • Price$4.00 / $20.00
    • Context1.05M
01 — Verdict

Gemini 4 Neon is our pick

Gemini 4 Neon is the better all-round choice, scoring 70/100 against GPT-5.6 Sol (64) and Claude Fable 5 (62). It leads on capability, price and inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%. Capability uses the average of shared benchmarks (GPQA Diamond, FrontierMath Tiers 1–3, OTIS Mock AIME 2024–2025 and SimpleQA Verified), because Gemini 4 Neon has no Capabilities Index score yet.Gemini 4 Neon is the better all-round choice, scoring 89/100 against GPT-5.6 Sol (83) and Claude Fable 5 (83). It leads on capability and inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%. Capability uses the average of shared benchmarks (GPQA Diamond, FrontierMath Tiers 1–3, OTIS Mock AIME 2024–2025 and SimpleQA Verified), because Gemini 4 Neon has no Capabilities Index score yet.

  • CapabilityGemini 4 NeonShared benchmarks: Gemini 4 Neon 90.7% · GPT-5.6 Sol 88.1% · Claude Fable 5 87.9%
  • Lowest priceGemini 4 NeonGemini 4 Neon $6.00 · GPT-5.6 Sol $8.00 · Claude Fable 5 $20.00 per 1M tokens (3:1 blend)
  • Longest contextGPT-5.6 Sol and Gemini 4 NeonGPT-5.6 Sol 1,050,000 · Gemini 4 Neon 1,048,576 · Claude Fable 5 1,000,000 tokens
  • Widest inputsGemini 4 NeonClaude Fable 5: Text, Images, PDFs · Gemini 4 Neon: Text, Images, PDFs, Audio, Video · GPT-5.6 Sol: Text, Images, PDFs
  • Self-hostingNo confirmed open weightsAll three are available only through APIs
How the score is built
MeasureWeightClaude Fable 5Gemini 4 NeonGPT-5.6 Sol
CapabilityShared benchmarks50%889188
Price25%0127
Inputs & features15%8010080
Context window10%646565
Overall100%62/10070/10064/100
How the score is built
MeasureWeightClaude Fable 5Gemini 4 NeonGPT-5.6 Sol
CapabilityShared benchmarks67%889188
Inputs & features20%8010080
Context window13%646565
Overall100%83/10089/10083/100
02 — Side by side

Every spec in one table

Highlighted cells lead their row. Unavailable specifications are marked “Not published”. Publisher results include their evaluation settings and source.

Claude Fable 5 vs Gemini 4 Neon vs GPT-5.6 Sol specifications side by side
SpecificationClaude Fable 5AnthropicGemini 4 NeonGoogleGPT-5.6 SolOpenAI
TaskNot publishedMultimodal reasoningNot published
Published capabilitiesClaude model for creative writing, analysis, and controlled agent workflowsReasons across documents, code, images, audio and video in one context.Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows
AccessNot publishedPaid Gemini API, Google AI Studio, and eligible Gemini subscriptionsNot published
SourcesNot publishedPublisher documentation · Publisher documentationNot published
Capability
Capabilities Index (ECI)164.2 (best)Not published163.0
ECI rank#13 of 159 (best)Not published#15 of 159
ECI confidence interval161.8–166.9Not published160.7–165.6
ECI evaluation dateJun 9, 2026Not publishedJul 9, 2026
Documented capabilitiesClaude model for creative writing, analysis, and controlled agent workflowsReasons across documents, code, images, audio and video in one context.Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows
Model parametersNot publishedNot publishedNot published
Output modalitiesTextTextText
GPQA DiamondGraduate-level science questions93.9%max96.3%xhigh (best)93.5%max
FrontierMath Tiers 1–3Research-level mathematics87.0%max91.2%xhigh (best)89.1%max
OTIS Mock AIME 2024–2025Competition mathematics100%high100%xhigh100%max
SimpleQA VerifiedShort factual questions70.7%xhigh75.2%xhigh (best)69.7%max
Publisher-reported benchmarks
SWE-Bench ProPublisher-reported result80.3resolve rateReported resultJun 9, 2026Not published64.6resolve rateReported resultJul 9, 2026
SWE-Bench VerifiedPublisher-reported result95resolvedReported resultNot publishedNot published
Terminal-Bench 2.1Publisher-reported result88success rateReported resultJun 9, 2026Not published88.8success rateReported resultJul 9, 2026
Humanity's Last Examno tools59accuracyReported resultJun 9, 2026Not publishedNot published
Humanity's Last Examwith tools64.5accuracyReported resultJun 9, 2026Not publishedNot published
OSWorld-VerifiedPublisher-reported result85success rateReported resultJun 9, 2026Not publishedNot published
FrontierCode · Diamondhigh effort29.3pass rateReported resultJun 9, 2026Not publishedNot published
GDPval-AAPublisher-reported result1932EloReported resultJun 9, 2026Not publishedNot published
AutomationBenchPublisher-reported result17.4success rateReported resultJun 9, 2026Not publishedNot published
DeepSWE 1.1Publisher-reported resultNot publishedNot published72.7resolve rateReported resultJul 9, 2026
GPQA DiamondPublisher-reported resultNot publishedNot published94.6accuracyReported resultJul 9, 2026
FrontierMath v2 · Tier 1-3Publisher-reported resultNot publishedNot published89accuracyReported resultJul 9, 2026
BrowseCompPublisher-reported resultNot publishedNot published90.4accuracyReported resultJul 9, 2026
OSWorld 2.0Publisher-reported resultNot publishedNot published62.6success rateReported resultJul 9, 2026
MMMU Prono toolsNot publishedNot published83accuracyReported resultJul 9, 2026
Agents' Last ExamPublisher-reported resultNot publishedNot published52.7Reported resultJul 9, 2026
ToolathlonPublisher-reported resultNot publishedNot published58success rateReported resultJul 9, 2026
Artificial Analysis Intelligence Index 4.1maxNot publishedNot published58.9index scoreReported resultJul 9, 2026
Artificial Analysis Coding Agent Index 1.1maxNot publishedNot published80index scoreReported resultJul 9, 2026
Price per million tokens
Input$10.00$3.00 (best)$4.00
Output$50.00$15.00 (best)$20.00
Cached input$1.00$0.15 (best)$0.40
Blended (3:1)$20.00$6.00 (best)$8.00
Long-context rateSame rateSame rateOver 272K: $8.00 / $30.00
Price sourceOfficial Anthropic APIOfficial Google APIOfficial OpenAI API
Limits
Context window1,000,000 tokens1,048,576 tokens1,050,000 tokens (best)
Max inputNot publishedNot published922,000 tokens
Max output128,000 tokens (best)65,536 tokens128,000 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsYesYesYes
AudioNoYesNo
VideoNoYesNo
ReasoningYeslow · medium · high · xhigh · maxYeslow · medium · high · xhighYeslow · medium · high · xhigh · max
Tool callingYesYesYes
Structured outputYesYesYes
File attachmentsYesYesYes
Temperature controlNoYesYes
Reasoning controleffortefforteffort
Availability
WeightsProprietaryProprietaryProprietary
API model IDclaude-fable-5gemini-4-neongpt-5.6-sol
API providers551861 (best)
ReleasedJun 9, 2026Nov 18, 2026Jul 9, 2026
Knowledge cutoffJan 31, 2026Mar 2026Feb 16, 2026
Publisher documentationPublisher documentationPublisher documentation · Publisher documentationPublisher documentation
Source metadata updatedJun 9, 2026Nov 18, 2026Jul 9, 2026
Data sourcesmodels.dev · Epoch AImodels.dev · Epoch AImodels.dev · Epoch AI
Catalog checkedNov 22, 2026Nov 22, 2026Nov 22, 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$200.00
  • Gemini 4 Neon$60.00
  • GPT-5.6 Sol$80.00
04 — Questions

Which should you choose?

Which is better: Claude Fable 5, Gemini 4 Neon or GPT-5.6 Sol?

Gemini 4 Neon is the better all-round choice, scoring 70/100 against GPT-5.6 Sol (64) and Claude Fable 5 (62). It leads on capability, price and inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%. Capability uses the average of shared benchmarks (GPQA Diamond, FrontierMath Tiers 1–3, OTIS Mock AIME 2024–2025 and SimpleQA Verified), because Gemini 4 Neon has no Capabilities Index score yet.Gemini 4 Neon is the better all-round choice, scoring 89/100 against GPT-5.6 Sol (83) and Claude Fable 5 (83). It leads on capability and inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%. Capability uses the average of shared benchmarks (GPQA Diamond, FrontierMath Tiers 1–3, OTIS Mock AIME 2024–2025 and SimpleQA Verified), because Gemini 4 Neon has no Capabilities Index score yet.

Which is cheaper, Claude Fable 5, Gemini 4 Neon or GPT-5.6 Sol?

Gemini 4 Neon is cheaper at $3.00 input / $15.00 output per million tokens (official Google API price). GPT-5.6 Sol costs $4.00 input / $20.00 output per million tokens (official OpenAI API price); Claude Fable 5 costs $10.00 input / $50.00 output per million tokens (official Anthropic API price). At a typical mix of three input tokens to one output token, that is $6.00 per million tokens for Gemini 4 Neon versus $8.00 for GPT-5.6 Sol (1.3× as much) and $20.00 for Claude Fable 5 (3.3× as much).

Which scores higher on benchmarks?

Not every model here has a Capabilities Index score, so we compare the average of shared benchmarks (GPQA Diamond, FrontierMath Tiers 1–3, OTIS Mock AIME 2024–2025 and SimpleQA Verified): Gemini 4 Neon 90.7%, GPT-5.6 Sol 88.1% and Claude Fable 5 87.9%. On individual benchmarks: GPQA Diamond — Gemini 4 Neon 96.3%, Claude Fable 5 93.9%, GPT-5.6 Sol 93.5%; FrontierMath Tiers 1–3 — Gemini 4 Neon 91.2%, GPT-5.6 Sol 89.1%, Claude Fable 5 87.0%; OTIS Mock AIME 2024–2025 — Claude Fable 5 100%, Gemini 4 Neon 100%, GPT-5.6 Sol 100%; SimpleQA Verified — Gemini 4 Neon 75.2%, Claude Fable 5 70.7%, GPT-5.6 Sol 69.7%.

Which is better for coding?

There are no published SWE-bench Verified results for Claude Fable 5, Gemini 4 Neon and GPT-5.6 Sol yet, so there is no like-for-like coding score. On overall capability, Gemini 4 Neon leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.

Which has the bigger context window?

GPT-5.6 Sol and Gemini 4 Neon have the largest context windows (1,050,000 and 1,048,576 tokens), against 1,000,000 for Claude Fable 5. Maximum output per response: Claude Fable 5 up to 128,000, Gemini 4 Neon up to 65,536, GPT-5.6 Sol up to 128,000 tokens.

Which can read images, PDFs, audio or video?

Claude Fable 5 accepts text, images and PDFs; Gemini 4 Neon accepts text, images, PDFs, audio and video; GPT-5.6 Sol accepts text, images and PDFs. Gemini 4 Neon handles the widest range of inputs.

Are any of these open source?

No. Claude Fable 5, Gemini 4 Neon and GPT-5.6 Sol are proprietary and only available through APIs and apps.

Which is newer?

Gemini 4 Neon is the newest, released Nov 18, 2026. GPT-5.6 Sol came out Jul 9, 2026; Claude Fable 5 came out Jun 9, 2026. Knowledge cutoff: Claude Fable 5 Jan 31, 2026, Gemini 4 Neon Mar 2026, GPT-5.6 Sol Feb 16, 2026.

How do you decide the winner?

This rating uses capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, 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 22, 2026.This rating uses capability (67%, independent benchmark results); inputs & features (20%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (13%, 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 22, 2026.