Gemini 4 Carbon vs Mimo v2 Pro
Full profiles: Gemini 4 Carbon (Google) and Mimo v2 Pro (Xiaomi): every benchmark, price and rank.
Updated · Data from 4 sources
As of 29 Oct 2026, Gemini 4 Carbon is ahead of Mimo v2 Pro on quality (65.1 vs 59.2 on the BenchLeader Index), but Mimo v2 Pro is 2.7× cheaper at $3.00 vs $8.00 per 1M tokens blended. Gemini 4 Carbon leads in every category we measure both in.
Key facts (as of 29 Oct 2026)
- Gemini 4 Carbon scores 65.1 on the BenchLeader Index and Mimo v2 Pro scores 59.2 (BenchLeader, 29 Oct 2026).
- Gemini 4 Carbon costs $8.00 per 1M tokens blended (list price, 29 Oct 2026).
- Mimo v2 Pro costs $3.00 per 1M tokens blended (list price, 29 Oct 2026).
- Of the 4 benchmarks both models have, Gemini 4 Carbon leads 4 (BenchLeader, 29 Oct 2026).
Gemini 4 Carbon benchmarks 
Mimo v2 Pro benchmarks Which to pick for…
The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.
| Use case | Pick | Why | Confidence |
|---|---|---|---|
| Coding | Gemini 4 Carbon | 72 vs 52 category score | High |
| Reasoning | Gemini 4 Carbon | 79 vs 64 category score; Humanity's Last Exam (AA) 60.4% vs 30.4% | High |
| Long documents | Gemini 4 Carbon | 65 vs 59 category score; AA-LCR v1.1 79.3% vs 68.3% | Medium |
| Chat quality (human preference) | – | Only Mimo v2 Pro has an Arena rating (63 category score) | Not comparable |
| High volume on a budget | Neither flagship | A smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs | – |
Key differences
- Gemini 4 Carbon (high) leads on quality: 65.1 vs 59.2.
- Gemini 4 Carbon (high) is stronger in coding, knowledge, long context, reasoning.
- Mimo v2 Pro is stronger in agents & tools, human preference, instruction following, maths.
At a glance
| Spec | Gemini 4 Carbon | Mimo v2 Pro |
|---|---|---|
| Developer | Xiaomi | |
| Released | 28 Oct 2026 | 18 Mar 2026 |
| Context window (tokens) | 1,000,000 | 1,000,000 |
| Compared at | Gemini 4 Carbon (high) | Mimo v2 Pro |
| Open weights | No | No |
| Price in / out / cached input per 1M | $4.00 / $20.00 / – | – |
Category by category
Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.
| Category | Gemini 4 Carbon (high) | Mimo v2 Pro | Leader |
|---|---|---|---|
| Reasoning | 78.9 | 63.9 | Gemini 4 Carbon |
| Coding | 71.7 | 52.3 | Gemini 4 Carbon |
| Agents & tools | – | 69.4 | not comparable |
| Maths | – | 62.8 | not comparable |
| Knowledge | 75.8 | – | not comparable |
| Instruction following | – | 67.8 | not comparable |
| Human preference | – | 63.2 | not comparable |
| Long context | 64.5 | 58.8 | Gemini 4 Carbon |
Where sources disagree
Across the 4 benchmarks both have, Gemini 4 Carbon leads 4, Mimo v2 Pro leads 0. Every overall index that rates both puts Gemini 4 Carbon ahead.
| Overall index | Gemini 4 Carbon (high) | Mimo v2 Pro | Leader |
|---|---|---|---|
| BenchLeader Index | 65.1 | 59.2 | Gemini 4 Carbon |
Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).
Price, speed and latency
List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page; suite cost is what Artificial Analysis paid to run its whole Intelligence Index.
| Measure | Gemini 4 Carbon (high) | Mimo v2 Pro |
|---|---|---|
| Blended price per 1M tokens | $8.00 | – |
| Input / output per 1M | $4.00 / $20.00 | – / – |
| Price per task: chat reply | $0.0076 | – |
| Price per task: summarize a 30-page report | $0.060 | – |
| Price per task: code edit | $0.054 | – |
| Price per task: agentic coding session | $0.320 | – |
| Price per task: structured extraction | $0.012 | – |
| Cost to run a full benchmark suite | $7.76 | – |
| Output speed | 100 tok/s | – |
| Time to first answer | 103.1 s | – |
| Time to a complete answer | 108.1 s | – |
Each model is compared at its best-ranked reasoning-effort setting. Gemini 4 Carbon (high) scores 65.1 and takes 103 s to its first answer token. Mimo v2 Pro scores 59.2. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.
Every benchmark
46 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.
| Metric | Publisher | Gemini 4 Carbon (high) | Mimo v2 Pro |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 65.1 | 59.2 |
| Coding score | BenchLeader | 71.7 | 52.3 |
| Knowledge score | BenchLeader | 75.8 | – |
| Long context score | BenchLeader | 64.5 | 58.8 |
| Reasoning score | BenchLeader | 78.9 | 63.9 |
| Agents & tools score | BenchLeader | – | 69.4 |
| Human preference score | BenchLeader | – | 63.2 |
| Instruction following score | BenchLeader | – | 67.8 |
| Maths score | BenchLeader | – | 62.8 |
| Blended price $/M | BenchLeader | $8.00 | – |
| Output speed | BenchLeader | 100 tok/s | – |
| Time to first answer | BenchLeader | 103.1 s | – |
| Context window | BenchLeader | 1,000,000 tokens | 1,000,000 tokens |
| Reasoning | |||
| Arena Hard Prompts | Arena (LMArena) | – | 1475 |
| GPQA Diamond (AA) | Artificial Analysis | – | 87.0% |
| Humanity's Last Exam (AA) | Artificial Analysis | 60.4% | 30.4% |
| HLE-Diamond (AA) | Artificial Analysis | 69.1% | – |
| CritPt | Artificial Analysis | 36.0% | 0.3% |
| CritPt v2 hard subset (AA) | Artificial Analysis | 63.0% | – |
| CL-bench | Epoch AI Benchmarking Hub | – | 15.7% |
| CL-bench Life | Epoch AI Benchmarking Hub | – | 6.9% |
| Coding | |||
| SciCode | SciCode | 64.2% | – |
| Arena Coding | Arena (LMArena) | – | 1503 |
| Arena WebDev | Arena (LMArena) | – | 1434 |
| Vibe Code Bench v1.1 | Vals AI | 89.1% | – |
| ALE-Bench | Epoch AI Benchmarking Hub | – | 785.2 |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 65.2% | – |
| FrontierCode 1.1 (AA) | Artificial Analysis | 48.5% | – |
| FrontierCode 2.0 (AA) | Artificial Analysis | 40.6% | – |
| Agents & tools | |||
| Terminal-Bench Hard | Artificial Analysis | – | 40.9% |
| τ²-Bench Telecom (AA) | Artificial Analysis | – | 95.0% |
| Finance Agent v2.1 | Vals AI | 67.2% | – |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | 17.5% | – |
| Legal Research Bench | Vals AI | 55.8% | – |
| Tax Agent Bench | Vals AI | 48.9% | – |
| Terminal-Bench 4.0 (Vals) | Vals AI | 63.1% | – |
| Vending-Bench 2 | Andon Labs | 16484.2† | – |
| AutomationBench | Artificial Analysis | 77.8% | – |
Show all 46 benchmarks
| Metric | Publisher | Gemini 4 Carbon (high) | Mimo v2 Pro |
|---|---|---|---|
| Agents & tools | |||
| GDP.pdf (AA) | Artificial Analysis | 28.4% | – |
| AA-Briefcase v1.1 | Artificial Analysis | 1609 | – |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 64.8% | – |
| Maths | |||
| Arena Maths | Arena (LMArena) | – | 1450 |
| Knowledge | |||
| AA-Omniscience v1.1 | Artificial Analysis | 53.5 | – |
| Excel Modeling Benchmark v1.1 | Vals AI | 76.5% | – |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | 58.3% | – |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | 88.6% | – |
| Instruction following | |||
| IFBench | Artificial Analysis | – | 68.8% |
| Arena Instruction Following | Arena (LMArena) | – | 1445 |
| Human preference | |||
| Arena Text | Arena (LMArena) | – | 1448 |
| Arena Creative Writing | Arena (LMArena) | – | 1423 |
| Arena Multi-turn | Arena (LMArena) | – | 1466 |
| Arena Longer Queries | Arena (LMArena) | – | 1467 |
| Multimodal | |||
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | 58.6%† | – |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 79.3% | 68.3% |
| Composite | |||
| AA Intelligence Index v5.0 | Artificial Analysis | 59.4 | – |
| AA Intelligence Index v4.3.2 | Artificial Analysis | – | 28.6 |
| AA Progress Index v1 | Artificial Analysis | 351.6 | 279 |
| Vals Index | Vals AI | 70.4 | – |
| Vals Finance Index | Vals AI | 66.3% | – |
Data as of 2026-10-29. Best configuration of each model; every score links to its source on the model pages.
What changed
- Mimo v2 Pro: BenchLeader Index 59.7 → 59.2.
- Mimo v2 Pro: 1 new result (AA Progress Index v1).
- Mimo v2 Pro: BenchLeader Index 60.2 → 59.7.
Related comparisons
- Gemini 4 Carbon vs Claude Opus 5.5
- Gemini 4 Carbon vs GPT-6 Astra
- Gemini 4 Carbon vs GPT-6.1 Sol
- Mimo v2 Pro vs Claude Opus 5.5
- Mimo v2 Pro vs GPT-6 Astra
- Mimo v2 Pro vs GPT-6.1 Sol
- Mimo v2 Pro vs Claude Fable 5.1
- Gemini 4 Argon vs Mimo v2 Pro
Rankings: Best LLM overall · Best LLM for coding · Best LLM for agents · Best cheap LLMs
Gemini 4 Carbon vs Mimo v2 Pro: questions
- Is Gemini 4 Carbon better than Mimo v2 Pro?
- Gemini 4 Carbon (high) leads on quality: 65.1 vs 59.2. The BenchLeader Index combines every independent quality benchmark; Gemini 4 Carbon (high) is ahead overall as of 29 Oct 2026, but check the category scores for your use.
- Gemini 4 Carbon vs Mimo v2 Pro: which is cheaper, and will that change?
- Mimo v2 Pro is cheaper today: $3.00 against $8.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is Gemini 4 Carbon or Mimo v2 Pro better for coding?
- Gemini 4 Carbon scores higher in coding (72 vs 52 on the category index, where 50 is average).
- Which is better for long documents?
- Gemini 4 Carbon scores higher on long-context benchmarks (65 vs 59). Both accept 1,000,000 tokens of context.
- Do independent benchmarks agree on Gemini 4 Carbon vs Mimo v2 Pro?
- Across the 4 benchmarks both have, Gemini 4 Carbon leads 4, Mimo v2 Pro leads 0. Every overall index that rates both puts Gemini 4 Carbon ahead.
More questions (1)
- When was Gemini 4 Carbon released?
- Gemini 4 Carbon was released on 28 Oct 2026.