ZMIME
Comparison · 3 models · Updated Nov 22, 2026

Gemini 4 Carbon vs Claude Haiku 5.5 vs GPT-6.1 Sol

Claude Haiku 5.5 comes out ahead, 82 to 75 and 71 on our weighted score, and it is the cheaper option too.Gemini 4 Carbon comes out ahead, 93 to 88 and 83 on our weighted score, though Claude Haiku 5.5 is 20× cheaper per token.

  1. Google

    Gemini 4 Carbon

    Released Nov 10, 2026

    75/100
    • ECI169.7
    • Price$2.00 / $10.00
    • Context1.05M
  2. Our pick

    Anthropic

    Claude Haiku 5.5

    Released Oct 7, 2026Latest

    82/100
    • ECI160.3
    • Price$0.10 / $0.50
    • Context1M
  3. OpenAI

    GPT-6.1 Sol

    Released Sep 29, 2026

    71/100
    • ECI168.6
    • Price$2.00 / $10.00
    • Context1.05M
  4. Our pick

    Google

    Gemini 4 Carbon

    Released Nov 10, 2026

    93/100
    • ECI169.7
    • Price$2.00 / $10.00
    • Context1.05M
  5. Anthropic

    Claude Haiku 5.5

    Released Oct 7, 2026Latest

    83/100
    • ECI160.3
    • Price$0.10 / $0.50
    • Context1M
  6. OpenAI

    GPT-6.1 Sol

    Released Sep 29, 2026

    88/100
    • ECI168.6
    • Price$2.00 / $10.00
    • Context1.05M
01 — Verdict

Claude Haiku 5.5 is our pickGemini 4 Carbon is our pick

Claude Haiku 5.5 is the better all-round choice, scoring 82/100 against Gemini 4 Carbon (75) and GPT-6.1 Sol (71). It leads on price. Gemini 4 Carbon wins on inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.Gemini 4 Carbon is the better all-round choice, scoring 93/100 against GPT-6.1 Sol (88) and Claude Haiku 5.5 (83). It leads on inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.

  • CapabilityGemini 4 CarbonCapabilities Index (ECI): Gemini 4 Carbon 169.7 · GPT-6.1 Sol 168.6 · Claude Haiku 5.5 160.3
  • Lowest priceClaude Haiku 5.5Claude Haiku 5.5 $0.20 · Gemini 4 Carbon $4.00 · GPT-6.1 Sol $4.00 per 1M tokens (3:1 blend)
  • Longest contextGPT-6.1 Sol and Gemini 4 CarbonGPT-6.1 Sol 1,050,000 · Gemini 4 Carbon 1,048,576 · Claude Haiku 5.5 1,000,000 tokens
  • Widest inputsGemini 4 CarbonGemini 4 Carbon: Text, Images, PDFs, Audio, Video · Claude Haiku 5.5: Text, Images, PDFs · GPT-6.1 Sol: Text, Images, PDFs
  • Self-hostingNo confirmed open weightsAll three are available only through APIs
How the score is built
MeasureWeightGemini 4 CarbonClaude Haiku 5.5GPT-6.1 Sol
CapabilityCapabilities Index (ECI)50%978896
Price25%207920
Inputs & features15%1008080
Context window10%656465
Overall100%75/10082/10071/100
How the score is built
MeasureWeightGemini 4 CarbonClaude Haiku 5.5GPT-6.1 Sol
CapabilityCapabilities Index (ECI)67%978896
Inputs & features20%1008080
Context window13%656465
Overall100%93/10083/10088/100
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.

Gemini 4 Carbon vs Claude Haiku 5.5 vs GPT-6.1 Sol specifications side by side
SpecificationGemini 4 CarbonGoogleClaude Haiku 5.5AnthropicGPT-6.1 SolOpenAI
Capability
Capabilities Index (ECI)169.7 (best)160.3168.6
ECI rank#3 of 159 (best)#20 of 159#6 of 159
ECI confidence interval166.6–173.1158.2–162.7165.7–171.9
ECI evaluation dateNov 10, 2026Oct 7, 2026Sep 29, 2026
Documented capabilitiesGoogle's most capable reasoning model for complex software engineering, deep math and science, high factual accuracy, and long-horizon autonomous agentsFast Claude model for responsive assistance, classification, and lightweight agentsNear-Astra performance for complex coding, computer use, and professional work at a lower cost.
Model parametersNot publishedNot publishedNot published
Output modalitiesTextTextText
GPQA DiamondGraduate-level science questions96.5%high (best)89.7%max95.4%max
FrontierMath Tiers 1–3Research-level mathematics90.5%high75.1%max93.7%max (best)
OTIS Mock AIME 2024–2025Competition mathematics100%high (best)98.9%xhigh100%max (best)
SimpleQA VerifiedShort factual questions77.7%high (best)23.8%max73.9%max
Publisher-reported benchmarks
GDPval-AA 2.1Publisher-reported resultNot published1620EloReported resultOct 7, 2026Not published
AA-Briefcase 1.1Publisher-reported resultNot published1578EloReported resultOct 7, 2026Not published
OSWorld 2.1offline subsetNot published72.4partial scoreReported resultOct 7, 2026Not published
Humanity's Last Examno toolsNot published45.9scoreReported resultOct 7, 2026Not published
Humanity's Last Examwith toolsNot published57.4scoreReported resultOct 7, 2026Not published
Terminal-Bench 4.0Publisher-reported resultNot published39.2scoreReported resultOct 7, 2026Not published
FrontierCode 1.1 · MainPublisher-reported resultNot published46.4scoreReported resultOct 7, 2026Not published
Chartographyno toolsNot published46.4scoreReported resultOct 7, 2026Not published
Price per million tokens
Input$2.00$0.10 (best)$2.00
Output$10.00$0.50 (best)$10.00
Cached input$0.10$0.01 (best)$0.10
Blended (3:1)$4.00$0.20 (best)$4.00
Long-context rateSame rateOver 100K: $0.50 / $2.50Over 272K: $4.00 / $15.00
Price sourceOfficial Google APIOfficial Anthropic APIOfficial OpenAI API
Limits
Context window1,048,576 tokens1,000,000 tokens1,050,000 tokens (best)
Max inputNot publishedNot published922,000 tokens
Max output65,536 tokens128,000 tokens (best)128,000 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsYesYesYes
AudioYesNoNo
VideoYesNoNo
ReasoningYeslow · medium · highYeslow · medium · high · xhigh · maxYeslow · medium · high · xhigh · max
Tool callingYesYesYes
Structured outputYesYesYes
File attachmentsYesYesYes
Temperature controlYesNoNo
Reasoning controleffortefforteffort
Availability
WeightsProprietaryProprietaryProprietary
API model IDgemini-4-carbonclaude-haiku-5-5gpt-6.1-sol
API providers194851 (best)
ReleasedNov 10, 2026Oct 7, 2026Sep 29, 2026
Knowledge cutoffMar 2026Jun 2026Apr 30, 2026
Publisher documentationPublisher documentationPublisher documentationPublisher documentation
Source metadata updatedNov 10, 2026Oct 7, 2026Sep 29, 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.

  • Gemini 4 Carbon$40.00
  • Claude Haiku 5.5$2.00
  • GPT-6.1 Sol$40.00
04 — Questions

Which should you choose?

Which is better: Gemini 4 Carbon, Claude Haiku 5.5 or GPT-6.1 Sol?

Claude Haiku 5.5 is the better all-round choice, scoring 82/100 against Gemini 4 Carbon (75) and GPT-6.1 Sol (71). It leads on price. Gemini 4 Carbon wins on inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.Gemini 4 Carbon is the better all-round choice, scoring 93/100 against GPT-6.1 Sol (88) and Claude Haiku 5.5 (83). It leads on inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.

Which is cheaper, Gemini 4 Carbon, Claude Haiku 5.5 or GPT-6.1 Sol?

Claude Haiku 5.5 is cheaper at $0.10 input / $0.50 output per million tokens (official Anthropic API price). Gemini 4 Carbon costs $2.00 input / $10.00 output per million tokens (official Google API price); GPT-6.1 Sol costs $2.00 input / $10.00 output per million tokens (official OpenAI API price). At a typical mix of three input tokens to one output token, that is $0.20 per million tokens for Claude Haiku 5.5 versus $4.00 for Gemini 4 Carbon (20× as much) and $4.00 for GPT-6.1 Sol (20× as much).

Which scores higher on benchmarks?

Gemini 4 Carbon scores higher on the Capabilities Index (ECI): Gemini 4 Carbon 169.7 (#3 of 159), GPT-6.1 Sol 168.6 (#6 of 159) and Claude Haiku 5.5 160.3 (#20 of 159). The confidence ranges of the top two overlap (166.6–173.1 vs 165.7–171.9), so treat the gap as small. On individual benchmarks: GPQA Diamond — Gemini 4 Carbon 96.5%, GPT-6.1 Sol 95.4%, Claude Haiku 5.5 89.7%; FrontierMath Tiers 1–3 — GPT-6.1 Sol 93.7%, Gemini 4 Carbon 90.5%, Claude Haiku 5.5 75.1%; OTIS Mock AIME 2024–2025 — Gemini 4 Carbon 100%, GPT-6.1 Sol 100%, Claude Haiku 5.5 98.9%; SimpleQA Verified — Gemini 4 Carbon 77.7%, GPT-6.1 Sol 73.9%, Claude Haiku 5.5 23.8%.

Which is better for coding?

There are no published SWE-bench Verified results for Gemini 4 Carbon, Claude Haiku 5.5 and GPT-6.1 Sol yet, so there is no like-for-like coding score. On overall capability, Gemini 4 Carbon 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-6.1 Sol and Gemini 4 Carbon have the largest context windows (1,050,000 and 1,048,576 tokens), against 1,000,000 for Claude Haiku 5.5. Maximum output per response: Gemini 4 Carbon up to 65,536, Claude Haiku 5.5 up to 128,000, GPT-6.1 Sol up to 128,000 tokens.

Which can read images, PDFs, audio or video?

Gemini 4 Carbon accepts text, images, PDFs, audio and video; Claude Haiku 5.5 accepts text, images and PDFs; GPT-6.1 Sol accepts text, images and PDFs. Gemini 4 Carbon handles the widest range of inputs.

Are any of these open source?

No. Gemini 4 Carbon, Claude Haiku 5.5 and GPT-6.1 Sol are proprietary and only available through APIs and apps.

Which is newer?

Gemini 4 Carbon is the newest, released Nov 10, 2026. Claude Haiku 5.5 came out Oct 7, 2026; GPT-6.1 Sol came out Sep 29, 2026. Knowledge cutoff: Gemini 4 Carbon Mar 2026, Claude Haiku 5.5 Jun 2026, GPT-6.1 Sol Apr 30, 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.