ZMIME
Comparison · 3 models · Updated Nov 18, 2026

GPT-6.1 Sol vs Kimi K3 vs Gemini 4 Carbon

Gemini 4 Carbon comes out ahead, 75 to 71 and 64 on our weighted score.

Price in rating: Included · Exclude price

  1. OpenAI

    GPT-6.1 Sol

    Released Sep 29, 2026New

    71/100
    • ECI168.6
    • Price$2.00 / $10.00
    • Context1.05M
  2. Moonshot AI

    Kimi K3

    Released Jul 16, 2026

    64/100
    • ECI158.6
    • Price$3.00 / $15.00
    • Context1.05M
  3. Our pick

    Google

    Gemini 4 Carbon

    Released Nov 10, 2026New

    75/100
    • ECI169.8
    • Price$2.00 / $10.00
    • Context1.05M
01 — Verdict

Gemini 4 Carbon is our pick

Gemini 4 Carbon is the better all-round choice, scoring 75/100 against GPT-6.1 Sol (71) and Kimi K3 (64). It leads on inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityGemini 4 CarbonCapabilities Index (ECI): Gemini 4 Carbon 169.8 · GPT-6.1 Sol 168.6 · Kimi K3 158.6
  • Lowest priceGPT-6.1 Sol and Gemini 4 CarbonGPT-6.1 Sol $4.00 · Gemini 4 Carbon $4.00 · Kimi K3 $6.00 per 1M tokens (3:1 blend)
  • Longest contextAbout the sameGPT-6.1 Sol 1,050,000 · Kimi K3 1,048,576 · Gemini 4 Carbon 1,048,576 tokens
  • Widest inputsGemini 4 CarbonGPT-6.1 Sol: Text, Images, PDFs · Kimi K3: Text, Images, Video · Gemini 4 Carbon: Text, Images, PDFs, Audio, Video
  • Self-hostingKimi K3Publishes downloadable weights
How the score is built
MeasureWeightGPT-6.1 SolKimi K3Gemini 4 Carbon
CapabilityCapabilities Index (ECI)50%958596
Price25%201220
Inputs & features15%8080100
Context window10%656565
Overall100%71/10064/10075/100
02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

GPT-6.1 Sol vs Kimi K3 vs Gemini 4 Carbon specifications side by side
SpecificationGPT-6.1 SolOpenAIKimi K3Moonshot AIGemini 4 CarbonGoogle
Capability
Capabilities Index (ECI)168.6158.6169.8 (best)
ECI rank#6 of 158#25 of 158#3 of 158 (best)
GPQA DiamondGraduate-level science questions95.4%93.1%96.5% (best)
FrontierMath Tiers 1–3Research-level mathematics93.7% (best)72.2%90.5%
OTIS Mock AIME 2024–2025Competition mathematics100% (best)97.2%100% (best)
SimpleQA VerifiedShort factual questions73.9%50.6%77.7% (best)
Price per million tokens
Input$2.00 (best)$3.00$2.00 (best)
Output$10.00 (best)$15.00$10.00 (best)
Cached input$0.10 (best)$0.30$0.10 (best)
Blended (3:1)$4.00 (best)$6.00$4.00 (best)
Long-context rateOver 272K: $4.00 / $15.00Same rateSame rate
Price sourceOfficial OpenAI APIOfficial Moonshot AI APIOfficial Google API
Limits
Context window1,050,000 tokens (best)1,048,576 tokens1,048,576 tokens
Max output128,000 tokens1,048,576 tokens (best)65,536 tokens
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsYesNoYes
AudioNoNoYes
VideoNoYesYes
ReasoningYeslow · medium · high · xhigh · maxYeslow · high · maxYeslow · medium · high
Tool callingYesYesYes
Structured outputYesYesYes
Availability
WeightsProprietaryOpenProprietary
API model IDgpt-6.1-solkimi-k3gemini-4-carbon
API providers5194 (best)18
ReleasedSep 29, 2026Jul 16, 2026Nov 10, 2026
Knowledge cutoffApr 30, 2026—Mar 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-6.1 Sol$40.00
  • Kimi K3$60.00
  • Gemini 4 Carbon$40.00
04 — Questions

Which should you choose?

Which is better: GPT-6.1 Sol, Kimi K3 or Gemini 4 Carbon?

Gemini 4 Carbon is the better all-round choice, scoring 75/100 against GPT-6.1 Sol (71) and Kimi K3 (64). It leads on inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, GPT-6.1 Sol, Kimi K3 or Gemini 4 Carbon?

GPT-6.1 Sol is cheaper at $2.00 input / $10.00 output per million tokens (official OpenAI API price). Gemini 4 Carbon costs $2.00 input / $10.00 output per million tokens (official Google API price); Kimi K3 costs $3.00 input / $15.00 output per million tokens (official Moonshot AI API price). At a typical mix of three input tokens to one output token, that is $4.00 per million tokens for GPT-6.1 Sol versus $4.00 for Gemini 4 Carbon (1× as much) and $6.00 for Kimi K3 (1.5× as much).

Which scores higher on benchmarks?

Gemini 4 Carbon scores higher on the Capabilities Index (ECI): Gemini 4 Carbon 169.8 (#3 of 158), GPT-6.1 Sol 168.6 (#6 of 158) and Kimi K3 158.6 (#25 of 158). The confidence ranges of the top two overlap (166.6–173.3 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%, Kimi K3 93.1%; FrontierMath Tiers 1–3 — GPT-6.1 Sol 93.7%, Gemini 4 Carbon 90.5%, Kimi K3 72.2%; OTIS Mock AIME 2024–2025 — GPT-6.1 Sol 100%, Gemini 4 Carbon 100%, Kimi K3 97.2%; SimpleQA Verified — Gemini 4 Carbon 77.7%, GPT-6.1 Sol 73.9%, Kimi K3 50.6%.

Which is better for coding?

There are no published SWE-bench Verified results for GPT-6.1 Sol, Kimi K3 and Gemini 4 Carbon 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?

Their context windows are effectively the same size: GPT-6.1 Sol 1,050,000, Kimi K3 1,048,576 and Gemini 4 Carbon 1,048,576 tokens. Maximum output per response: GPT-6.1 Sol up to 128,000, Kimi K3 up to 1,048,576, Gemini 4 Carbon up to 65,536 tokens.

Which can read images, PDFs, audio or video?

GPT-6.1 Sol accepts text, images and PDFs; Kimi K3 accepts text, images and video; Gemini 4 Carbon accepts text, images, PDFs, audio and video. Gemini 4 Carbon handles the widest range of inputs.

Are any of these open source?

Kimi K3 publishes its weights and can be self-hosted; GPT-6.1 Sol and Gemini 4 Carbon is proprietary.

Which is newer?

Gemini 4 Carbon is the newest, released Nov 10, 2026. GPT-6.1 Sol came out Sep 29, 2026; Kimi K3 came out Jul 16, 2026. Knowledge cutoff: GPT-6.1 Sol Apr 30, 2026, Gemini 4 Carbon Mar 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 18, 2026.