ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Kimi K2 Instruct vs Qwen3 235B-A22B Thinking 2507 vs WizardLM 2 8x22B

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

Price in rating: Excluded · Include price

  1. Moonshot AI

    Kimi K2 Instruct

    Released Jul 11, 2025

    28/100
    • ECI141.3
    • Price$0.57 / $2.30
    • Context131K
  2. Alibaba (Qwen)

    Qwen3 235B-A22B Thinking 2507

    Released Jul 25, 2025

    38/100
    • ECI143.3
    • Price$0.30 / $2.90
    • Context262K
  3. Microsoft

    WizardLM 2 8x22B

    Released Apr 15, 2024

    9/100
    • ECI—
    • Price$0.493 / $0.493
    • Context66K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Qwen3 235B-A22B Thinking 2507 38/100, Kimi K2 Instruct 28/100, WizardLM 2 8x22B 9/100) 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 priceWizardLM 2 8x22BWizardLM 2 8x22B $0.493 · Qwen3 235B-A22B Thinking 2507 $0.95 · Kimi K2 Instruct $1.00 per 1M tokens (3:1 blend)
  • Longest contextQwen3 235B-A22B Thinking 2507Qwen3 235B-A22B Thinking 2507 262,144 · Kimi K2 Instruct 131,072 · WizardLM 2 8x22B 65,536 tokens
  • Widest inputsSame inputsKimi K2 Instruct: Text · Qwen3 235B-A22B Thinking 2507: Text · WizardLM 2 8x22B: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightKimi K2 InstructQwen3 235B-A22B Thinking 2507WizardLM 2 8x22B
Inputs & features60%25350
Context window40%324322
Specs only100%28/10038/1009/100

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.

Kimi K2 Instruct vs Qwen3 235B-A22B Thinking 2507 vs WizardLM 2 8x22B specifications side by side
SpecificationKimi K2 InstructMoonshot AIQwen3 235B-A22B Thinking 2507Alibaba (Qwen)WizardLM 2 8x22BMicrosoft
Capability
Capabilities Index (ECI)141.3143.3 (best)—
ECI rank#108 of 158#100 of 158 (best)—
GPQA DiamondGraduate-level science questions—80.1% (best)43.4%
OTIS Mock AIME 2024–2025Competition mathematics—86.7%—
SimpleQA VerifiedShort factual questions—40.4%—
Price per million tokens
Input$0.57$0.30 (best)$0.493
Output$2.30$2.90$0.493 (best)
Cached input———
Blended (3:1)$1.00$0.95$0.493 (best)
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 11 providersMedian of 11 providersMedian of 3 providers
Limits
Context window131,072 tokens262,144 tokens (best)65,536 tokens
Max output32,768 tokens81,920 tokens (best)8,000 tokens
Inputs and features
TextYesYesYes
ImagesNoNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoYesNo
Tool callingYesYesNo
Structured outputNoNoNo
Availability
WeightsOpenModified MITOpenApache 2.0OpenApache-2.0
API model ID———
API providers1112 (best)3
ReleasedJul 11, 2025Jul 25, 2025Apr 15, 2024
Knowledge cutoff———
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.

  • Kimi K2 Instruct$10.30
  • Qwen3 235B-A22B Thinking 2507$8.80
  • WizardLM 2 8x22B$5.92
04 — Questions

Which should you choose?

Which is better: Kimi K2 Instruct, Qwen3 235B-A22B Thinking 2507 or WizardLM 2 8x22B?

There is not enough shared capability evidence to name an overall winner. The scores (Qwen3 235B-A22B Thinking 2507 38/100, Kimi K2 Instruct 28/100, WizardLM 2 8x22B 9/100) 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, Kimi K2 Instruct, Qwen3 235B-A22B Thinking 2507 or WizardLM 2 8x22B?

WizardLM 2 8x22B is cheaper at $0.493 input / $0.493 output per million tokens (median across 3 API providers). Qwen3 235B-A22B Thinking 2507 costs $0.30 input / $2.90 output per million tokens (median across 11 API providers); 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 $0.493 per million tokens for WizardLM 2 8x22B versus $0.95 for Qwen3 235B-A22B Thinking 2507 (1.9× as much) and $1.00 for Kimi K2 Instruct (2× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Kimi K2 Instruct has an ECI of 141.3, Qwen3 235B-A22B Thinking 2507 has an ECI of 143.3 and WizardLM 2 8x22B has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Kimi K2 Instruct, Qwen3 235B-A22B Thinking 2507 and WizardLM 2 8x22B yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that WizardLM 2 8x22B does not support tool calling, which most coding agents need.

Which has the bigger context window?

Qwen3 235B-A22B Thinking 2507 has the largest context window at 262,144 tokens, against 131,072 for Kimi K2 Instruct and 65,536 for WizardLM 2 8x22B. Maximum output per response: Kimi K2 Instruct up to 32,768, Qwen3 235B-A22B Thinking 2507 up to 81,920, WizardLM 2 8x22B up to 8,000 tokens.

Which can read images, PDFs, audio or video?

Kimi K2 Instruct accepts text; Qwen3 235B-A22B Thinking 2507 accepts text; WizardLM 2 8x22B accepts text. They handle the same number of input types.

Are any of these open source?

Yes, all three publish their weights (Modified MIT, Apache 2.0 and Apache-2.0), so you can self-host them.

Which is newer?

Qwen3 235B-A22B Thinking 2507 is the newest, released Jul 25, 2025. Kimi K2 Instruct came out Jul 11, 2025; WizardLM 2 8x22B came out Apr 15, 2024.

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.