Gemini 4 Carbon vs Kimi K3.1 Pro Together
Full profiles: Gemini 4 Carbon (Google) and Kimi K3.1 Pro Together (Moonshot AI): every benchmark, price and rank.
Updated · Data from 5 sources
As of 9 Nov 2026, Gemini 4 Carbon is ahead of Kimi K3.1 Pro Together on quality (68.5 vs 60.5 on the BenchLeader Index). Gemini 4 Carbon leads in every category we measure both in.
Key facts (as of 9 Nov 2026)
- Gemini 4 Carbon scores 68.5 on the BenchLeader Index and Kimi K3.1 Pro Together scores 60.5 (BenchLeader, 9 Nov 2026).
- Gemini 4 Carbon costs $8.00 per 1M tokens blended (list price, 9 Nov 2026).
Gemini 4 Carbon benchmarks high Google
Kimi K3.1 Pro Together benchmarks max Moonshot AIAdd a third modelWhich 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 |
|---|---|---|---|
| Reasoning | Gemini 4 Carbon | 77 vs 67 category score | High |
| Knowledge | Gemini 4 Carbon | 74 vs 68 category score | Medium |
| Chat quality (human preference) | – | Only Gemini 4 Carbon has an Arena rating (73 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: 68.5 vs 60.5.
- Gemini 4 Carbon (high) is stronger in agents & tools, coding, human preference, knowledge, long context, reasoning.
- Kimi K3.1 Pro Together (max) is stronger in maths.
At a glance
| Spec | Gemini 4 Carbon | Kimi K3.1 Pro Together |
|---|---|---|
| Developer | Moonshot AI | |
| Released | 28 Oct 2026 | 23 Oct 2026 |
| Context window (tokens) | 1,000,000 | – |
| Compared at | Gemini 4 Carbon (high) | Kimi K3.1 Pro Together (max) |
| 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) | Kimi K3.1 Pro Together (max) | Leader |
|---|---|---|---|
| Reasoning | 76.9 | 67.1 | Gemini 4 Carbon |
| Coding | 74.5 | – | not comparable |
| Agents & tools | 78.2 | – | not comparable |
| Maths | – | 65.8 | not comparable |
| Knowledge | 74.3 | 67.6 | Gemini 4 Carbon |
| Human preference | 72.8 | – | not comparable |
| Long context | 64.3 | – | not comparable |
On one chart
Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.
Dashed: that model has no result on the axis it crosses; the line only joins its neighbours.
Not drawn, no result for these models: Instruction following, Multimodal.
Where sources disagree
Across the 0 benchmarks both have, Gemini 4 Carbon leads 0, Kimi K3.1 Pro Together leads 0. Every overall index that rates both puts Gemini 4 Carbon ahead.
| Overall index | Gemini 4 Carbon (high) | Kimi K3.1 Pro Together (max) | Leader |
|---|---|---|---|
| BenchLeader Index | 68.5 | 60.5 | 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. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.
| Measure | Gemini 4 Carbon (high) | Kimi K3.1 Pro Together (max) |
|---|---|---|
| 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 per benchmark task (AA Index) | $7.76 | – |
| Output tokens per task (AA Index) | 123k | – |
| Of which reasoning | 72k | – |
| Time per task (AA Index) | 27 min | – |
| Output speed | 75 tok/s | – |
| Time to first answer | 69.4 s | – |
| Time to a complete answer | 160.3 s | – |
Each model is compared at its best-ranked reasoning-effort setting. Gemini 4 Carbon (high) scores 68.5 and takes 69 s to its first answer token; Gemini 4 Carbon (medium) scores 64.1 in 27 s. Kimi K3.1 Pro Together (max) scores 60.5. 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) | Kimi K3.1 Pro Together (max) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 68.5 | 60.5 |
| Agents & tools score | BenchLeader | 78.2 | – |
| Coding score | BenchLeader | 74.5 | – |
| Human preference score | BenchLeader | 72.8 | – |
| Knowledge score | BenchLeader | 74.3 | 67.6 |
| Long context score | BenchLeader | 64.3 | – |
| Reasoning score | BenchLeader | 76.9 | 67.1 |
| Maths score | BenchLeader | – | 65.8 |
| Blended price $/M | BenchLeader | $8.00 | – |
| Output speed | BenchLeader | 75 tok/s | – |
| Time to first answer | BenchLeader | 69.4 s | – |
| Context window | BenchLeader | 1,000,000 tokens | – |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | – | 94.2% |
| Arena Hard Prompts | Arena (LMArena) | 1547 | – |
| HLE-Diamond (AA) | Artificial Analysis | 69.1% | – |
| CritPt v2 hard subset (AA) | Artificial Analysis | 69.0% | – |
| Chess Puzzles | Epoch AI Benchmarking Hub | – | 45.0% |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | – | 42.0% |
| Coding | |||
| SciCode | SciCode | 64.2% | – |
| Arena Coding | Arena (LMArena) | 1567 | – |
| Arena WebDev | Arena (LMArena) | 1768 | – |
| Vibe Code Bench v1.1 | Vals AI | 89.1% | – |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 65.2% | – |
| FrontierCode 2.0 (AA) | Artificial Analysis | 40.6% | – |
| Agents & tools | |||
| Arena Agent | Arena (LMArena) | 16.6 | – |
| GDPval-AA v2.1 | Artificial Analysis | 1733 | – |
| 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 | 51.8% | – |
| Terminal-Bench 4.0 (Vals) | Vals AI | 63.1% | – |
| Vending-Bench 2 | Andon Labs | 16484.2† | – |
| AutomationBench | Artificial Analysis | 77.8% | – |
| GDP.pdf (AA) | Artificial Analysis | 28.4% | – |
| AA-Briefcase v1.1 | Artificial Analysis | 1611 | – |
| GDPx | GDPx by SemiAnalysis | 10.9% | – |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 64.8% | – |
Show all 46 benchmarks
| Metric | Publisher | Gemini 4 Carbon (high) | Kimi K3.1 Pro Together (max) |
|---|---|---|---|
| Agents & tools | |||
| FACTS Search | 94.4%† | – | |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | – | 78.3% |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | – | 65.8% |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | – | 100.0% |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | – | 62.2% |
| 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 | |||
| Arena Instruction Following | Arena (LMArena) | 1526 | – |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1527 | – |
| Arena Creative Writing | Arena (LMArena) | 1518 | – |
| Arena Multi-turn | Arena (LMArena) | 1564 | – |
| Arena Longer Queries | Arena (LMArena) | 1539 | – |
| Multimodal | |||
| MMMU-Pro | Artificial Analysis | 89.3%† | – |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | 58.6%† | – |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 79.3% | – |
| Composite | |||
| AA Intelligence Index v5.0 | Artificial Analysis | 60.0 | – |
| AA Progress Index v1 | Artificial Analysis | 350.8 | – |
| Vals Index | Vals AI | 70.5 | – |
| Vals Finance Index | Vals AI | 67.0% | – |
Data as of 2026-11-09. Best configuration of each model; every score links to its source on the model pages.
What changed
- Gemini 4 Carbon (high): BenchLeader Index 69.3 → 68.5.
- Gemini 4 Carbon (high): BenchLeader Index 68.8 → 69.3.
- Gemini 4 Carbon (high): 1 score revision.
- Kimi K3.1 Pro Together (max): first results.
- Gemini 4 Carbon (high): 2 score revisions.
- Gemini 4 Carbon (high): 1 score revision.
- Gemini 4 Carbon (high): 2 score revisions.
- Gemini 4 Carbon (high): 1 score revision.
Related comparisons
- Gemini 4 Carbon vs Claude Fable 5.2
- Gemini 4 Carbon vs Claude Opus 5.5
- Gemini 4 Carbon vs GPT-6 Astra
- Kimi K3.1 Pro Together vs Claude Fable 5.2
- Kimi K3.1 Pro Together vs Claude Opus 5.5
- Kimi K3.1 Pro Together vs GPT-6 Astra
- Gemini 4 Argon vs Kimi K3.1 Pro Together
- Gemini 4 Carbon vs Kimi K3
Rankings: Best LLM overall · Best LLM for coding · Best LLM for agents · Best cheap LLMs
Gemini 4 Carbon vs Kimi K3.1 Pro Together: questions
- Is Gemini 4 Carbon better than Kimi K3.1 Pro Together?
- Gemini 4 Carbon (high) leads on quality: 68.5 vs 60.5. The BenchLeader Index combines every independent quality benchmark; Gemini 4 Carbon (high) is ahead overall as of 9 Nov 2026, but check the category scores for your use.
- When was Gemini 4 Carbon released?
- Gemini 4 Carbon was released on 28 Oct 2026.