ZMIME
Comparison · 3 models · Updated Nov 18, 2026

GPT-5 Nano vs Kimi K2 Instruct vs Qwen3.5 9B

Too close to call on our weighted score (Qwen3.5 9B 71, GPT-5 Nano 71, Kimi K2 Instruct 53). The right pick depends on what you value most.

Price in rating: Included · Exclude price

  1. OpenAI

    GPT-5 Nano

    Released Aug 7, 2025

    71/100
    • ECI139.1
    • Price$0.05 / $0.40
    • Context400K
  2. Moonshot AI

    Kimi K2 Instruct

    Released Jul 11, 2025

    53/100
    • ECI141.3
    • Price$0.57 / $2.30
    • Context131K
  3. Alibaba (Qwen)

    Qwen3.5 9B

    Released Feb 23, 2026

    71/100
    • ECI139.5
    • Price$0.10 / $0.19
    • Context262K
01 — Verdict

Too close to call

It is close. Our weighted score puts them within a point (Qwen3.5 9B 71/100, GPT-5 Nano 71/100, Kimi K2 Instruct 53/100), so choose by what matters most for your work: Kimi K2 Instruct for raw capability, Qwen3.5 9B on price and GPT-5 Nano for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityKimi K2 InstructCapabilities Index (ECI): Kimi K2 Instruct 141.3 · Qwen3.5 9B 139.5 · GPT-5 Nano 139.1
  • Lowest priceQwen3.5 9BQwen3.5 9B $0.122 · GPT-5 Nano $0.138 · Kimi K2 Instruct $1.00 per 1M tokens (3:1 blend)
  • Longest contextGPT-5 NanoGPT-5 Nano 400,000 · Qwen3.5 9B 262,144 · Kimi K2 Instruct 131,072 tokens
  • Widest inputsQwen3.5 9BGPT-5 Nano: Text, Images · Kimi K2 Instruct: Text · Qwen3.5 9B: Text, Images, Video
  • Self-hostingKimi K2 Instruct and Qwen3.5 9BPublishes downloadable weights (Modified MIT)
How the score is built
MeasureWeightGPT-5 NanoKimi K2 InstructQwen3.5 9B
CapabilityCapabilities Index (ECI)50%676967
Price25%874889
Inputs & features15%702570
Context window10%503243
Overall100%71/10053/10071/100
02 — Side by side

Every spec in one table

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

GPT-5 Nano vs Kimi K2 Instruct vs Qwen3.5 9B specifications side by side
SpecificationGPT-5 NanoOpenAIKimi K2 InstructMoonshot AIQwen3.5 9BAlibaba (Qwen)
Capability
Capabilities Index (ECI)139.1141.3 (best)139.5
ECI rank#117 of 158#108 of 158 (best)#116 of 158
GPQA DiamondGraduate-level science questions69.4%—79.0% (best)
FrontierMath Tiers 1–3Research-level mathematics20.0%——
OTIS Mock AIME 2024–2025Competition mathematics81.1% (best)—61.7%
SimpleQA VerifiedShort factual questions11.7%——
Price per million tokens
Input$0.05 (best)$0.57$0.10
Output$0.40$2.30$0.19 (best)
Cached input$0.005——
Blended (3:1)$0.138$1.00$0.122 (best)
Long-context rateSame rateSame rateSame rate
Price sourceOfficial OpenAI APIMedian of 11 providersMedian of 20 providers
Limits
Context window400,000 tokens (best)131,072 tokens262,144 tokens
Max output128,000 tokens (best)32,768 tokens65,536 tokens
Inputs and features
TextYesYesYes
ImagesYesNoYes
PDFsNoNoNo
AudioNoNoNo
VideoNoNoYes
ReasoningYesminimal · low · medium · highNoYes
Tool callingYesYesYes
Structured outputYesNoNo
Availability
WeightsProprietaryOpenModified MITOpen
API model IDgpt-5-nano——
API providers30 (best)1122
ReleasedAug 7, 2025Jul 11, 2025Feb 23, 2026
Knowledge cutoffMay 30, 2024——
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-5 Nano$1.30
  • Kimi K2 Instruct$10.30
  • Qwen3.5 9B$1.38
04 — Questions

Which should you choose?

Which is better: GPT-5 Nano, Kimi K2 Instruct or Qwen3.5 9B?

It is close. Our weighted score puts them within a point (Qwen3.5 9B 71/100, GPT-5 Nano 71/100, Kimi K2 Instruct 53/100), so choose by what matters most for your work: Kimi K2 Instruct for raw capability, Qwen3.5 9B on price and GPT-5 Nano for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, GPT-5 Nano, Kimi K2 Instruct or Qwen3.5 9B?

Qwen3.5 9B is cheaper at $0.10 input / $0.19 output per million tokens (median across 20 API providers). GPT-5 Nano costs $0.05 input / $0.40 output per million tokens (official OpenAI API price); Kimi K2 Instruct costs $0.57 input / $2.30 output per million tokens (median across 11 API providers). At a typical mix of three input tokens to one output token, that is $0.122 per million tokens for Qwen3.5 9B versus $0.138 for GPT-5 Nano (1.1× as much) and $1.00 for Kimi K2 Instruct (8.2× as much).

Which scores higher on benchmarks?

Kimi K2 Instruct scores higher on the Capabilities Index (ECI): Kimi K2 Instruct 141.3 (#108 of 158), Qwen3.5 9B 139.5 (#116 of 158) and GPT-5 Nano 139.1 (#117 of 158). The confidence ranges of the top two overlap (138.3–144.0 vs 137.3–141.7), so treat the gap as small.

Which is better for coding?

There are no published SWE-bench Verified results for GPT-5 Nano, Kimi K2 Instruct and Qwen3.5 9B yet, so there is no like-for-like coding score. On overall capability, Kimi K2 Instruct 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 Nano has the largest context window at 400,000 tokens, against 262,144 for Qwen3.5 9B and 131,072 for Kimi K2 Instruct. Maximum output per response: GPT-5 Nano up to 128,000, Kimi K2 Instruct up to 32,768, Qwen3.5 9B up to 65,536 tokens.

Which can read images, PDFs, audio or video?

GPT-5 Nano accepts text and images; Kimi K2 Instruct accepts text; Qwen3.5 9B accepts text, images and video. Qwen3.5 9B handles the widest range of inputs.

Are any of these open source?

Kimi K2 Instruct and Qwen3.5 9B publishes its weights (Modified MIT) and can be self-hosted; GPT-5 Nano is proprietary.

Which is newer?

Qwen3.5 9B is the newest, released Feb 23, 2026. GPT-5 Nano came out Aug 7, 2025; Kimi K2 Instruct came out Jul 11, 2025. Knowledge cutoff: GPT-5 Nano May 30, 2024.

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.