Side by side · November 2026

Gemini 4 Carbon vs MiMo-V2.6-Pro

Gemini 4 Carbon scores higher on the Models at Work leaderboard (77 vs 73 out of 100). On independent tests alone, Gemini 4 Carbon is ahead (97 vs 71). MiMo-V2.6-Pro is cheaper: 1,000 support replies cost about $1.64 at list price, against $10 on Gemini 4 Carbon, which is 6.1 times as much. On the Artificial Analysis Intelligence Index, one of the independent tests, Gemini 4 Carbon leads 60 to 30.

Updated Nov 18, 2026 · every number links to who measured it
Gemini 4 Carbon · GoogleMiMo-V2.6-Pro · Xiaomi
Leaderboard rank#3#5
Score (0–100)7773
Kind of workHardest problemsRun it yourself
Price per 1M tokens$2 to read · $10 to write$0.43 to read · $0.87 to write
Reads at once1M tokens (about 750,000 words)1M tokens (about 750,000 words)
Where you can get itGemini Enterprise Agent Platform (Google Cloud), Google AI Studio, Gemini for business, Gemini app (Google AI Ultra)OpenRouter
Can a company host it itselfNoYes (open weights)
Artificial Analysis Intelligence Index6030
Vals Finance Index67.05% (rank 1)57.85% (rank 19)
Vals Tax Agent Bench51.78% (rank 2)32.39% (rank 25)
Vals Legal Research Bench55.77% (rank 1)47.12% (rank 18)
Professional Reasoning Benchmark - Legal (Scale)53.35Not measured
Humanity's Sixth Sense (Scale)71.1025.20
Arena Text scoreNot measured1480 (rank 26)
Arena WebDev scoreNot measured1629 (rank 19)
Best forReading and comparing large sets of dense documents, Legal and finance analysis, Multi-step researchOvernight batch analysis, Running AI on your own servers, Replacing a mid-priced closed model

Cost of 1,000 jobs

1,000 of theseGemini 4 CarbonMiMo-V2.6-Pro
Support repliesthe customer message, the account notes and two help articles read; a 300-word reply written$10$1.64
Documents processeda two-page invoice or form read; the fields pulled out$7$1.12
Calls summariseda 40-minute call transcript read; a summary and next steps written$26$4.82
Contracts revieweda 40-page contract read against a checklist; a memo of issues written$75$14
Drafts writtena brief and one example read; a 600-word email or proposal section written$11$1.34

Worked out from each vendor’s list price and a fixed size for each job. A product built on a model charges its own price on top. See what every model costs for the same jobs.

Choose Gemini 4 Carbon for

  • Reading and comparing large sets of dense documents
  • Legal and finance analysis
  • Multi-step research

First on Vals AI's tests of finance work (67.1%) and legal research (55.8%) and second on Artificial Analysis's index (60 against the leader's 65), at a quarter of the leader's list price until 30 November, when Google doubles it.

Caveats: The $2 in / $10 out per million tokens (the unit vendors bill by) is introductory; Google says $4 / $20 applies after 30 November 2026, which will lower its score here. Google says it uses more text per task than Gemini 4 Argon, so the bill can run higher at the same list price. The rankings quoted in Google's launch post are relayed by Google and are not counted; six independent tests are. In the Gemini app it is for Google AI Ultra subscribers only, per Google; commenters on lower plans and one enterprise account report they cannot select it yet. It ranks 3rd, behind two cheaper models that are within three points of it: a tie. Expect it to fall when the price doubles on 1 December.

Choose MiMo-V2.6-Pro for

  • Overnight batch analysis
  • Running AI on your own servers
  • Replacing a mid-priced closed model

Xiaomi's open model costs about a fifteenth of Claude Opus 5.5 at list price and scores 30 on Artificial Analysis's index, level with the other open leaders; it is slow and long-winded.

Caveats: It writes long chains of working-out even on simple edits, which you pay for and wait for. About 47 tokens (word-pieces) a second on Xiaomi's own service, far slower than the fast models here. The only place to buy we confirmed is OpenRouter, a reseller that passes requests to Xiaomi and four other hosts; no major US cloud was found carrying it. The blind-vote ranking (Arena) rests on about 4,000 votes and is still settling. It ranks 5th. One reseller is the only route we confirmed, which holds its score down. Places 4 to 8 sit within three points of each other, which is a tie.

What people running them say

Gemini 4 Carbon: On the Hacker News (a developer forum) thread about Google's launch, several commenters on the Pro and Plus plans say Carbon shows in the app as Ultra-only, one says their company's enterprise account cannot use it yet, and another says their workplace already finds Argon too expensive. None of this is verified, and it is too little to score.

MiMo-V2.6-Pro: Hacker News, a developer forum (1,130 upvotes), was won over less by test scores than by Xiaomi's openness: a live view of the model's training, with progress charts, dropped datasets and running cost estimates. Users call it 'incredibly cheap' for test results level with Meta's Muse Spark and say it keeps DeepSeek and GLM 'in check'. The complaints agree: 'faster than DeepSeek but still much slower than leading models', and it 'seems to overthink way too much'. Several recommend buying it through OpenRouter, a reseller, rather than the vendor's own service in China.

Questions people ask

Which is better, Gemini 4 Carbon or MiMo-V2.6-Pro?

Gemini 4 Carbon scores higher on the Models at Work leaderboard (77 vs 73 out of 100). On independent tests alone, Gemini 4 Carbon is ahead (97 vs 71). MiMo-V2.6-Pro is cheaper: 1,000 support replies cost about $1.64 at list price, against $10 on Gemini 4 Carbon, which is 6.1 times as much. On the Artificial Analysis Intelligence Index, one of the independent tests, Gemini 4 Carbon leads 60 to 30.

When should I choose Gemini 4 Carbon over MiMo-V2.6-Pro?

Choose Gemini 4 Carbon for reading and comparing large sets of dense documents, legal and finance analysis, multi-step research. First on Vals AI's tests of finance work (67.1%) and legal research (55.8%) and second on Artificial Analysis's index (60 against the leader's 65), at a quarter of the leader's list price until 30 November, when Google doubles it.

When should I choose MiMo-V2.6-Pro over Gemini 4 Carbon?

Choose MiMo-V2.6-Pro for overnight batch analysis, running ai on your own servers, replacing a mid-priced closed model. Xiaomi's open model costs about a fifteenth of Claude Opus 5.5 at list price and scores 30 on Artificial Analysis's index, level with the other open leaders; it is slow and long-winded.

Which is cheaper, Gemini 4 Carbon or MiMo-V2.6-Pro?

Gemini 4 Carbon costs $2 per million tokens it reads (input) and $10 per million tokens it writes (output) on Google's list price (Google: Gemini 4 Carbon is now available, read Nov 18, 2026). A token is about three-quarters of a word. MiMo-V2.6-Pro costs $0.43 per million tokens it reads (input) and $0.87 per million tokens it writes (output) on Xiaomi's list price (MiMo-V2.6-Pro - Artificial Analysis, read Nov 18, 2026). A token is about three-quarters of a word.

What do 1,000 jobs cost on Gemini 4 Carbon and MiMo-V2.6-Pro?

At list price: 1,000 support replies cost $10 on Gemini 4 Carbon and $1.64 on MiMo-V2.6-Pro; 1,000 documents processed cost $7 on Gemini 4 Carbon and $1.12 on MiMo-V2.6-Pro; 1,000 calls summarised cost $26 on Gemini 4 Carbon and $4.82 on MiMo-V2.6-Pro; 1,000 contracts reviewed cost $75 on Gemini 4 Carbon and $14 on MiMo-V2.6-Pro; 1,000 drafts written cost $11 on Gemini 4 Carbon and $1.34 on MiMo-V2.6-Pro. A product built on either model charges its own price on top.

Scores come from the Models at Work leaderboard: Score is 0 to 100 and computed, not typed. 40% is independent testing (Artificial Analysis, Arena, Scale, Epoch, Vals and others; each test is scaled against the best score on this board, and tests of real work, such as finished freelance projects or professional tasks, count double the exams). 30% is price: the vendor's list price for a typical mix of reading and writing, on a fixed scale from $0.05 to $60 per million tokens, so a model that costs a fifth as much gains real ground. 15% is what people report after running it, from Signals and linked threads. 15% is fit: how much text it can take in at once and where a business can get it (the products and clouds that carry it), with a small credit for open weights. A missing component drops out and the rest are reweighted. A model with no independent test yet is provisional and ranks below every measured one. Within three points is a tie. Vendor-published figures are labelled and never counted. Prices are vendor list prices where published; a typical mix assumes three parts reading to one part writing.