Skip to main content

text model comparison

Kimi K3.1 Pro vs Qwen4-Max

Kimi K3.1 Pro and Qwen4-Max are both current text models, from Moonshot Kimi and Alibaba Qwen. Qwen4-Max is 25% cheaper per 1M input tokens than Kimi K3.1 Pro, $1.50 vs $2. On Arena WebDev, Kimi K3.1 Pro scores 1686 Elo and Qwen4-Max 1750 Elo (Arena, measured November 15, 2026). Both accept about 1.05M tokens of context (1,048,576 and 1,000,000).

Higher Arena WebDev
Qwen4-Max1750 Elo against 1686 Elo
Lower price per 1M input tokens
Qwen4-Max$1.50 against $2
Longer context window
Kimi K3.1 Pro1.05M tokens against 1M tokens
Newer release
Qwen4-MaxNov 2026 against Oct 2026

Data verified November 17, 2026 · Dataset 2026-11-17

Share this

Side by side

Kimi K3.1 Pro and Qwen4-Max, line by line

Prices in effect today, compared at the same tier wherever both list one. The better value in each row is highlighted.

FactKimi K3.1 ProQwen4-Max
Price
Price per 1M input tokens$2$1.50 (better)
Price per 1M output tokens$10$4.50 (better)
Independent benchmarks
Arena WebDev1686 Elo (#9 of 46)Range 1677 to 16961750 Elo (#6 of 46) (better)Range 1734 to 1765
Arena Text1485 Elo (#10 of 50)Range 1475 to 1495Not measured
Epoch Capabilities Index161.4 points (#12 of 43)Range 159 to 164Not measured
GPQA Diamond94.2% (#10 of 40)Not measured
FrontierMath Tiers 1-3 (v2)78.2% (#17 of 39)Not measured
SimpleQA Verified62.2% (#13 of 36)Not measured
Specs
ProviderMoonshot KimiAlibaba Qwen
Release dateOctober 23, 2026November 16, 2026
AccessAPI and open weightsAPI only
Context window1,048,576 tokens1,000,000 tokens
Max output1,048,576 tokens131,072 tokens
Inputtext, image, videotext, image, video
Outputtexttext

Ranges under the scores are the publishers' own: published rating ranges from Arena and 90% credible intervals from Epoch AI. Where two ranges overlap, the gap is inside the measurement's own uncertainty, so the row says too close to call and neither score is highlighted or counted as a lead.

Scores:Arena · 2026-11-17Epoch AI · 2026-11-16

Open both in the interactive comparison

Provider results

What the labs report

Results tables a lab published with one of its models, where it lists both Kimi K3.1 Pro and Qwen4-Max. These are the lab's own figures, not independent measurements, and each table is read on its own: labs run benchmarks with different harnesses and budgets.

Qwen Team, Qwen4-Max launch chart, November 16, 2026Qwen Team · 2026-11-17

BenchmarkKimi K3.1 ProQwen4-Max
DeepSWE v1.175.5%75.7% (better)
Terminal-Bench 4.067.2% (better)48.5%
ProgramBench25.0%31.5% (better)
Agents' Last Exam v1.143.4%46.7% (better)
APEX-Agents v1.165.5%72.1% (better)
HealthBench Professional57.2%60.0% (better)
Humanity's Last Exam51.1%51.7% (better)
BioMysteryBench80.6%85.0% (better)
Chartography50.0%54.2% (better)

Alibaba's chart from the Qwen4-Max announcement. Qwen3.8-Max is the 0902 refresh, and Kimi K3.1 is Kimi K3.1 Pro: its DeepSWE and BioMysteryBench figures match Moonshot's own card. The APEX-Agents and Agents' Last Exam scores come from those benchmarks' leaderboards; Alibaba ran Chartography for its own two models with a larger image budget. Left out here: CodeArena and AgentArena (Arena ratings), AA-Briefcase and AutomationBench-AA (Artificial Analysis), HLAB-Vals-1.1 (taken from the Vals Index), and JobBench and Video-Index, which we could not confirm are public.

Charts

Against every current text model

Where Kimi K3.1 Pro and Qwen4-Max land among the current models of their task, on every independent benchmark, on price and on context.

Where each stands

On Arena WebDev, Kimi K3.1 Pro ranks #9 and Qwen4-Max #6 of 46 current models. Each bar is the share of current models it beats: on score, price and context.

Kimi K3.1 Pro and Qwen4-Max among the current text models, one row per benchmark, price and context window.

Independent benchmarks

Arena Text

Kimi K3.1 Pro:#10of 50

1,485 Elo · ahead of 80%

Published rating range 1,475 to 1,495

Qwen4-Max: Not scored

Arena WebDev

Kimi K3.1 Pro:#9of 46

1,686 Elo · ahead of 82%

Published rating range 1,677 to 1,696

Qwen4-Max:#6of 46

1,750 Elo · ahead of 89%

Published rating range 1,734 to 1,765

Epoch Capabilities Index

Kimi K3.1 Pro:#12of 43

161.4 · ahead of 74%

90% credible interval 159 to 164

Qwen4-Max: Not scored

GPQA Diamond

Kimi K3.1 Pro:#10of 40

94.2% · ahead of 77%

Qwen4-Max: Not scored

FrontierMath Tiers 1-3 (v2)

Kimi K3.1 Pro:#17of 39

78.2% · ahead of 58%

Qwen4-Max: Not scored

Price and context

Price per 1M input tokens

Kimi K3.1 Pro:#36of 60

$2 · cheaper than 22%

Qwen4-Max:#33of 60

$1.50 · cheaper than 42%

Price per 1M output tokens

Kimi K3.1 Pro:#41of 60

$10 · cheaper than 24%

Qwen4-Max:#32of 60

$4.50 · cheaper than 47%

Context window

Kimi K3.1 Pro:#12of 71

1.05M tokens · longer than 60%

Qwen4-Max:#33of 71

1M tokens · longer than 21%

Quality against price

Arena Text · measured November 11, 2026

Kimi K3.1 Pro scores 1,485 at $4 (blended price per 1M tokens). The line joins the current models no other beats on both price and Arena Text score; hover any point to name it.

Quality against priceArena Text score against price for 42 text models, Kimi K3.1 Pro and Qwen4-Max marked.1,2501,3001,3501,4001,4501,5001,550$0.30$1$3$10MOST ATTRACTIVE QUADRANTMedian price $2.58Median 1,473Blended price per 1M tokens (3 input : 1 output), log scaleArena Text (Elo)Kimi K3.1 Pro
Quality against price: the data
Arena Text score against price for 42 text models, Kimi K3.1 Pro and Qwen4-Max marked.
ModelProviderBlended price per 1M tokensArena Text (Elo)
Gemini 4 CarbonGoogle$41,526
Gemini 4 ArgonGoogle$41,522
Muse WonderMeta$81,511
Claude Opus 5.5Anthropic$81,507
Gemini 3.8 FlashGoogle$1.501,497
Muse Spark 1.3Meta$21,497
Gemini 4 HydrogenGoogle$31,490
Kimi K3Moonshot Kimi$61,487
GPT-5.6 SolOpenAI$81,485
Kimi K3.1 ProMoonshot Kimi$41,485
Qwen3.8-MaxAlibaba Qwen$31,484
Gemini 3.6 FlashGoogle$31,483
GLM-5.3Z.ai$2.151,482
GPT-5.5OpenAI$111,481
GPT-6.1 SolOpenAI$41,481
MiMo-V2.6-ProXiaomi MiMo$0.541,480
GPT-5.4OpenAI$5.631,475
DeepSeek-V4.1-FlashDeepSeek$0.521,475
GLM-5.3-FlashZ.ai$0.241,475
GPT-6 AstraOpenAI$201,474
Gemini 3 Flash PreviewGoogle$1.131,473
Claude Sonnet 5.5Anthropic$41,473
Grok 4.20xAI$1.561,472
GPT-5.6 TerraOpenAI$4.501,468
Grok 4.5xAI$31,466
DeepSeek-V4-ProDeepSeek$1.981,464
Grok 4.6xAI$31,457
GPT-6 SolOpenAI$41,457
Gemini 3.5 Flash-LiteGoogle$0.851,455
GPT-5.6 LunaOpenAI$0.451,453
Step 5 PreviewStepFun$1.431,449
MiMo-V2.6-FlashXiaomi MiMo$0.181,448
Grok 4.7xAI$31,443
Grok 4.3xAI$1.561,442
GPT-6 LunaOpenAI$0.201,441
Claude Haiku 5.5Anthropic$0.201,421
Mistral Large 4Mistral AI$1.051,420
GPT-4.1OpenAI$3.501,415
Inkling 2 SmallThinking Machines Lab$0.471,412
Solar Pro 4Upstage$0.521,387
GPT-4.1 miniOpenAI$0.701,383
GPT-4.1 nanoOpenAI$0.181,322

Cost

What each costs

Example workloads at each provider's listed rates, then every other rate either one lists. The cheaper figure in each row is highlighted.

The same work, priced

For 10M input and 2M output tokens, Kimi K3.1 Pro costs 1.7 times as much as Qwen4-Max, at each provider's listed rates.

What Kimi K3.1 Pro and Qwen4-Max cost for the same work, at the rates each provider lists.
  • 10M input and 2M output tokens

    Kimi K3.1 Pro costs 1.7× as much

    Kimi K3.1 Pro
    $40
    Qwen4-Max
    $24
  • The same, with 9M of the input tokens cached

    Kimi K3.1 Pro costs 2.1× as much

    Kimi K3.1 Pro
    $23.80
    Qwen4-Max
    $11.18
Workload or rateKimi K3.1 ProQwen4-Max
Example workloads
10M input and 2M output tokens$40$24 (better)
The same, with 9M of the input tokens cached$23.80$11.18 (better)
Other listed rates
1M input tokens, cached$0.20$0.075 (better)
1M input tokens, 5-minute cache write$2$1.875 (better)
1M input tokens, 1-hour cache write$4$3 (better)
1M input tokens, Highspeed endpoint$4Not listed
1M output tokens, Highspeed endpoint$20Not listed

Your own bill will differ. These figures use list prices and example workloads. The AI Model Cost Audit reviews your real usage, shortlists models that score as well for each task for less, and estimates the savings.

Launch price $100, regular price $150

See the cost audit

Verdict

When to choose each

Kimi K3.1 Pro

Where it leads

  • Longer responses, up to 1,048,576 vs 131,072 output tokens
  • Open weights you can run yourself

Best for

  • Long-horizon coding and agent work at mid-tier prices
  • Long documents, images and video in one 1M-token context

Watch out for

  • Thinking is always on: reasoning effort runs low, high or max, and max is the default
  • The Highspeed endpoint, two to three times faster by Moonshot's account, costs twice as much at $4 input and $20 output per 1M tokens
  • The weights carry Moonshot's own license: a model-as-a-service business above $20M in yearly revenue needs a separate agreement, and products above 100M monthly users or $20M monthly revenue must display the Kimi K3.1 Pro name
  • Self-hosting takes a multi-node GPU cluster: the MXFP4 weights alone are about 1.56 TB
  • Arena Text rates it 1485 on 3,995 votes (November 11, 2026), below Gemini 4 Carbon (1526) and level with Gemini 4 Hydrogen (1490) within the published ranges

Qwen4-Max

Where it leads

  • Lower input and output prices, $1.50 and $4.50 vs $2 and $10 per 1M tokens
  • Higher Arena WebDev score, 1750 Elo vs 1686 Elo
  • Cheaper cached input, $0.075 vs $0.20 per 1M tokens

Best for

  • Coding and long-horizon agent work at a lower price than Claude Opus 5.5 or GPT-6.1 Sol
  • Office deliverables and research over long documents, images and video in one 1M-token context

Watch out for

  • API only: Alibaba has not released the weights, and says only that smaller Qwen4 models are coming to open source
  • Artificial Analysis scores it 43 on its Intelligence Index against 59 for Claude Opus 5.5 (November 2026), and Alibaba's own chart has Opus 5.5 ahead on Terminal-Bench 4.0 (59.6% against 48.5%) and ProgramBench (65.0% against 31.5%), with Kimi K3.1 Pro at 67.2% on Terminal-Bench
  • The recorded rates are the Singapore (international) price; Beijing and the Global regions charge $1.413 input and $4.24 output per 1M tokens, and there is no batch discount
  • Arena Text has not rated it yet, and its WebDev rating rests on 1,814 votes so far

From benchmark to production

Building on Kimi K3.1 Pro or Qwen4-Max?

Public scores rarely hold on your own data. We test both models on your real tasks, then build the agent or pipeline around the one that wins.

AI Model Cost AuditLaunch price $100, regular price $150

FAQ

Kimi K3.1 Pro vs Qwen4-Max FAQ

Which is cheaper, Kimi K3.1 Pro or Qwen4-Max?

Qwen4-Max is 25% cheaper per 1M input tokens than Kimi K3.1 Pro, $1.50 vs $2. For 10M input and 2M output tokens, Kimi K3.1 Pro costs $40 and Qwen4-Max $24 at standard rates.

Which is cheaper with prompt caching, Kimi K3.1 Pro or Qwen4-Max?

Kimi K3.1 Pro charges $0.20 per 1M cached input tokens, 90% below its standard input rate, and Qwen4-Max $0.075, 95% below. With 9M of 10M input tokens cached and 2M output tokens, Kimi K3.1 Pro costs $23.80 and Qwen4-Max $11.18.

Which scores higher on independent benchmarks, Kimi K3.1 Pro or Qwen4-Max?

Qwen4-Max leads on Arena WebDev, 1750 Elo to 1686 Elo. Scores are independent evaluations, not either vendor's launch figures.

How do Kimi K3.1 Pro and Qwen4-Max compare in Qwen Team's own results?

In the Qwen4-Max launch chart (November 16, 2026), Qwen4-Max leads on DeepSWE v1.1, 75.7% to 75.5%; Kimi K3.1 Pro leads on Terminal-Bench 4.0, 67.2% to 48.5%; Qwen4-Max leads on ProgramBench, 31.5% to 25.0%. These are Qwen Team's figures, not independent measurements.

Which has the larger context window, Kimi K3.1 Pro or Qwen4-Max?

Both accept about 1.05M tokens of context (1,048,576 and 1,000,000). Kimi K3.1 Pro returns up to 1,048,576 tokens per response, Qwen4-Max 131,072.

Can I run Kimi K3.1 Pro or Qwen4-Max myself?

Kimi K3.1 Pro is released as open weights you can run yourself; Qwen4-Max is available through its provider's API only.

AI Model Brief

The AI models worth knowing, once a week

What shipped, how it scores on independent benchmarks, what it costs per million tokens and what was deprecated, from the data behind our AI model benchmarks.

One email a week. We send a confirmation link first, and every issue has a one-click unsubscribe.

We use your address only to send the brief. See our privacy policy.

See this week’s brief

Production evaluation

Choosing between Kimi K3.1 Pro and Qwen4-Max?

Public benchmarks narrow the shortlist. We run both on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.

  • A head-to-head evaluation on your real workload
  • Routing between models by cost and difficulty