Gemini 3.8 Flash vs Kimi K3.1 Pro
Full profiles: Gemini 3.8 Flash (Google) and Kimi K3.1 Pro (Moonshot AI): every benchmark, price and rank.
Updated · Data from 10 sources
As of 24 Oct 2026, Gemini 3.8 Flash (high) and Kimi K3.1 Pro are neck and neck on quality (64.4 vs 66.8 on the BenchLeader Index, inside the ±7.3 margin of error), and Gemini 3.8 Flash (high) costs 2.7× less, which makes it the better buy for most workloads. Gemini 3.8 Flash (high)'s current price runs until 31 Dec 2026; from 1 Jan 2027 Gemini 3.8 Flash (high) costs 1.3× less ($3.00 vs $4.00 per 1M blended).
Gemini 3.8 Flash benchmarks high Google
Kimi K3.1 Pro benchmarks Moonshot AIOpen in the comparison toolWhich 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 |
|---|---|---|---|
| Agents & tool use | Kimi K3.1 Pro | 67 vs 51 category score; CWE-Bench (AA) 60.8% vs 52.5% | High |
| Reasoning | Kimi K3.1 Pro | 81 vs 68 category score; CritPt 24.6% vs 18.3% | High |
| Knowledge | Kimi K3.1 Pro | 75 vs 68 category score; AA-Omniscience 29.5 vs 29.6 | Medium |
| Long documents | Kimi K3.1 Pro | 68 vs 66 category score; AA-LCR 86.3% vs 81.3% | Medium |
| Images and other media | Either | 68 vs 67 category score; MMMU-Pro 85.6% vs 83.9% | Either |
| Chat quality (human preference) | – | Only Gemini 3.8 Flash has an Arena rating (69 category score) | Not comparable |
| Lowest cost | Gemini 3.8 Flash | $1.50 vs $4.00 per 1M blended; agentic coding session $0.060 vs $0.160; from 1 Jan 2027: $3.00 vs $4.00 | – |
| Fastest first answer | Either | 25.1 s (Gemini 3.8 Flash (high)) vs 27.7 s (Kimi K3.1 Pro) to the first answer token | – |
| High volume on a budget | Neither flagship | A smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs | – |
Key differences
- Gemini 3.8 Flash (high) and Kimi K3.1 Pro are neck and neck on quality (64.4 vs 66.8, within the ±7.3 margin).
- Gemini 3.8 Flash (high) is stronger in coding, human preference, maths, multimodal.
- Kimi K3.1 Pro is stronger in agents & tools, composite, knowledge, long context, reasoning.
- Gemini 3.8 Flash (high) is 2.7× cheaper ($1.50 vs $4.00 per 1M blended) until 31 Dec 2026, then $3.00 vs $4.00 from 1 Jan 2027.
- Gemini 3.8 Flash (high) streams 1.8× faster (141 vs 81 tokens per second).
At a glance
| Spec | Gemini 3.8 Flash | Kimi K3.1 Pro |
|---|---|---|
| Developer | Moonshot AI | |
| Released | 2 Sept 2026 | 23 Oct 2026 |
| Context window (tokens) | 1,048,576 | 1,048,576 |
| Compared at | Gemini 3.8 Flash (high) | Kimi K3.1 Pro |
| Open weights | No | No |
| Price in / out / cached input per 1M | $0.750 / $3.75 / $0.075 | $2.00 / $10.00 / $0.200 |
| Announced price change | $1.50 / $7.50 from 1 Jan 2027 | None announced |
Limits, availability and announced prices from the vendors' own pages: ai.google.dev pricing (checked 20 Oct 2026). Everything else is from the day's data.
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 3.8 Flash (high) | Kimi K3.1 Pro | Leader |
|---|---|---|---|
| Reasoning | 68.2 | 81.3 | Kimi K3.1 Pro |
| Coding | 63.5 | – | not comparable |
| Agents & tools | 50.9 | 67.3 | Kimi K3.1 Pro |
| Maths | 62.4 | – | not comparable |
| Knowledge | 68.4 | 74.8 | Kimi K3.1 Pro |
| Human preference | 69.1 | – | not comparable |
| Multimodal | 67.7 | 67.0 | level |
| Long context | 65.7 | 68.3 | Kimi K3.1 Pro |
| Composite | 75.3 | 75.8 | level |
Where sources disagree
Across the 18 benchmarks both have, Gemini 3.8 Flash leads 3, Kimi K3.1 Pro leads 15. Every overall index that rates both puts Kimi K3.1 Pro ahead.
| Overall index | Gemini 3.8 Flash (high) | Kimi K3.1 Pro | Leader |
|---|---|---|---|
| BenchLeader Index | 64.4 | 66.8 | neck and neck |
| AA Intelligence Index v4.3.2 | 40.9 | 55.1 | Kimi K3.1 Pro |
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 3.8 Flash (high) | Kimi K3.1 Pro |
|---|---|---|
| Blended price per 1M tokens, until 31 Dec 2026 | $1.50 | $4.00 |
| Input / output per 1M | $0.750 / $3.75 | $2.00 / $10.00 |
| Blended price per 1M from 1 Jan 2027 | $3.00 | $4.00 |
| Input / output per 1M from 1 Jan 2027 | $1.50 / $7.50 | $2.00 / $10.00 |
| Cached input per 1M | $0.075 | $0.200 |
| Price per task: chat reply | $0.0014 | $0.0038 |
| Price per task: summarize a 30-page report | $0.011 | $0.030 |
| Price per task: code edit | $0.010 | $0.027 |
| Price per task: agentic coding session | $0.060 | $0.160 |
| Price per task: structured extraction | $0.0023 | $0.0060 |
| Cost to run a full benchmark suite | $1.24 | $2.11 |
| Output speed | 141 tok/s | 81 tok/s |
| Time to first answer | 25.1 s | 27.7 s |
| Time to a complete answer | 28.7 s | 33.9 s |
Per token is not per task: on Artificial Analysis' full suite Gemini 3.8 Flash (high) cost $1.24 and Kimi K3.1 Pro $2.11, because Gemini 3.8 Flash (high) used about 1.6× as many tokens for the same work, which a per-token price hides.
Each model is compared at its best-ranked reasoning-effort setting. Gemini 3.8 Flash (high) scores 64.4 and takes 25 s to its first answer token; Gemini 3.8 Flash (medium) scores 64.4 in 3 s, Gemini 3.8 Flash (low) scores 61.0 in 3 s. Kimi K3.1 Pro scores 66.8 and takes 28 s to its first answer token. 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
136 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 3.8 Flash (high) | Kimi K3.1 Pro |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 64.4 | 66.8 |
| Agents & tools score | BenchLeader | 50.9 | 67.3 |
| Coding score | BenchLeader | 63.5 | – |
| Composite score | BenchLeader | 75.3 | 75.8 |
| Human preference score | BenchLeader | 69.1 | – |
| Knowledge score | BenchLeader | 68.4 | 74.8 |
| Long context score | BenchLeader | 65.7 | 68.3 |
| Maths score | BenchLeader | 62.4 | – |
| Multimodal score | BenchLeader | 67.7 | 67.0 |
| Reasoning score | BenchLeader | 68.2 | 81.3 |
| Blended price $/M | BenchLeader | $1.50 | $4.00 |
| Output speed | BenchLeader | 141 tok/s | 81 tok/s |
| Time to first answer | BenchLeader | 25.1 s | 27.7 s |
| Context window | BenchLeader | 1,048,576 tokens | 1,048,576 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 95.4% | – |
| Humanity's Last Exam | Scale AI / CAIS | 44.5%† | – |
| Arena Hard Prompts | Arena (LMArena) | 1517 | – |
| LiveBench 2.0 Reasoning | LiveBench | 89.3%† | 91.1% |
| LiveBench 1.0 Reasoning | LiveBench | 89.3% | – |
| GPQA Diamond (AA) | Artificial Analysis | 95.3% | – |
| Humanity's Last Exam (AA) | Artificial Analysis | 47.8% | 52.5% |
| GPQA Diamond (Vals) | Vals AI | 94.4% | – |
| ARC-AGI-1 | ARC Prize | 98.5% | – |
| ARC-AGI-2 | ARC Prize | 89.2% | – |
| ARC-AGI-3 | ARC Prize | 35.0% | – |
| CritPt | Artificial Analysis | 18.3% | 24.6% |
| MysteryMechanism | Vals AI | 36.5% | – |
| Chess Puzzles | Epoch AI Benchmarking Hub | 58.0% | – |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 47.0% | – |
| LMCA | Epoch AI Benchmarking Hub | 51.5%† | – |
| DTBench | Epoch AI Benchmarking Hub | 95.7%† | – |
| Coding | |||
| SciCode | SciCode | 56.6% | – |
| WeirdML | WeirdML | 84.8% | – |
| FrontierCode | Cognition | 41.2%† | – |
| Arena Coding | Arena (LMArena) | 1528 | – |
| Arena WebDev | Arena (LMArena) | 1585 | – |
| LiveBench 2.0 Coding | LiveBench | 82.2%† | 81.8% |
| LiveBench 1.0 Coding | LiveBench | 72.5% | – |
| SciCode (AA) | Artificial Analysis | 56.6% | 60.8% |
Show all 136 benchmarks
| Metric | Publisher | Gemini 3.8 Flash (high) | Kimi K3.1 Pro |
|---|---|---|---|
| Coding | |||
| LiveCodeBench | Vals AI | 89.5% | – |
| IOI | Vals AI | 56.9% | – |
| SWE-bench (Vals) | Vals AI | 80.0% | – |
| Code Migration | Vals AI | 36.5% | – |
| Code Migration v1.1 | Vals AI | 38.6% | – |
| ProgramBench | Vals AI | 1.0% | – |
| SWE-bench Multimodal | Vals AI | 40.8% | – |
| Vibe Code Bench 1-100 | Vals AI | 18.8% | – |
| Vibe Code Bench v1.1 | Vals AI | 78.7% | – |
| SWE Atlas: Codebase QnA | Scale AI SEAL | 47.0%† | – |
| SWE Atlas: Refactoring | Scale AI SEAL | 44.8%† | – |
| SWE Atlas: Test Writing | Scale AI SEAL | 53.7%† | – |
| Surface Evolver Bench | Epoch AI Benchmarking Hub | 76.9% | – |
| DeepSWE v1.1 | Epoch AI Benchmarking Hub | 73.8% | – |
| CursorBench | Cursor | 39.6% | – |
| ALE-Bench | Epoch AI Benchmarking Hub | 1269.7 | – |
| FrontierSWE | Epoch AI Benchmarking Hub | 19.6% | – |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 19.7% | 67.2% |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | 87.6% | – |
| Startrise Frontend | Startrise | 64.6%† | – |
| FrontierCode 1.1 (AA) | Artificial Analysis | 36.4% | 47.1% |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | 19.1% | – |
| Remote Labor Index | Scale AI / CAIS | 5.8%† | – |
| APEX-Agents | Mercor | 64.3%† | – |
| Arena Agent | Arena (LMArena) | 3.6 | – |
| LiveBench Long Agentic | LiveBench | 30.1%† | 49.5% |
| LiveBench Browser | LiveBench | 64.0%† | 80.0% |
| LiveBench Agentic Coding | LiveBench | 54.2% | – |
| Terminal-Bench 2.1 (Vals) | Vals AI | 81.3% | – |
| HiL-Bench | Scale AI SEAL | 41.5%† | – |
| GDPval-AA v2.1 | Artificial Analysis | 46.8% | 67.3% |
| τ³-Banking (AA) | Artificial Analysis | 45.0% | – |
| ITBench SRE (AA) | Artificial Analysis | 52.5% | – |
| Analyst Agent (AA) | Artificial Analysis | 46.3% | – |
| CUA-bench | Vals AI | 4.2% | – |
| CyberBench | Vals AI | 43.8% | – |
| Finance Agent v2 | Vals AI | 61.4% | – |
| Finance Agent v2.1 | Vals AI | 65.8% | – |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | 12.1% | – |
| Harvey's Legal Agent Benchmark v1 | Vals AI | 10.0% | – |
| Legal Research Bench | Vals AI | 38.9% | – |
| SkillsBench | Vals AI | 58.0% | – |
| SREBench | Vals AI | 11.1% | – |
| Tax Agent Bench | Vals AI | 32.1% | – |
| Terminal-Bench 4.0 (Vals) | Vals AI | 19.7% | – |
| Terminal-Bench Science | Vals AI | 8.6% | – |
| Time Horizon Index: KSP | Vals AI | 18.8% | – |
| Vending-Bench 2 | Andon Labs | 5093.8† | – |
| AutomationBench | Artificial Analysis | 59.9% | 73.3% |
| GDP.pdf (AA) | Artificial Analysis | 21.0% | 31.4% |
| Harvey LAB-AA v1.1 | Harvey | 0.0% | – |
| AA-Briefcase v1.1 | Artificial Analysis | 1202 | 1678 |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 10.0% | – |
| CWE-Bench (AA) | Artificial Analysis | 52.5% | 60.8% |
| DeepSec-Bench (AA) | Artificial Analysis | 14.5% | 36.7% |
| CyberGym end-to-end (AA) | Artificial Analysis | 8.4% | 94.7% |
| FACTS Search | 76.3%† | – | |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 68.4% | – |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 21.9% | – |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 98.9% | – |
| ProofBench | Vals AI | 48.0%† | – |
| LiveBench Mathematics | LiveBench | 91.6% | – |
| Arena Maths | Arena (LMArena) | 1526 | – |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 69.7% | – |
| LiveBench 2.0 Data Analysis | LiveBench | 54.0%† | 79.1% |
| LiveBench Research | LiveBench | 79.1%† | 77.9% |
| LiveBench 1.0 Data Analysis | LiveBench | 54.0% | – |
| AA-Omniscience | Artificial Analysis | 29.6 | 29.5 |
| MMLU-Pro | Vals AI | 90.2% | – |
| LegalBench | Vals AI | 87.0% | – |
| TaxEval | Vals AI | 74.5% | – |
| PRBench Finance | Scale AI SEAL | 49.5%† | – |
| PRBench Legal | Scale AI SEAL | 48.9%† | – |
| BioMysteryBench | Vals AI | 62.2% | – |
| Excel Modeling Benchmark | Vals AI | 72.2% | – |
| Excel Modeling Benchmark v1.1 | Vals AI | 72.9% | – |
| MedCode | Vals AI | 48.1% | – |
| MedScribe | Vals AI | 84.5% | – |
| Public Benefits Bench v1.1 | Vals AI | 65.3% | – |
| GDP.pdf | Epoch AI Benchmarking Hub | 23.2% | – |
| AA-Omniscience: accuracy | Artificial Analysis | 54.6% | 51.0% |
| AA-Omniscience: non-hallucination | Artificial Analysis | 44.8% | 56.1% |
| Instruction following | |||
| LiveBench Language | LiveBench | 87.8% | – |
| LiveBench Instruction Following | LiveBench | 81.4% | – |
| Arena Instruction Following | Arena (LMArena) | 1490 | – |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1496 | – |
| Arena Creative Writing | Arena (LMArena) | 1485 | – |
| Arena Multi-turn | Arena (LMArena) | 1504 | – |
| Arena Longer Queries | Arena (LMArena) | 1510 | – |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | 1315 | – |
| LiveBench Design | LiveBench | 72.7%† | 77.8% |
| MMMU-Pro | Artificial Analysis | 85.6% | 83.9% |
| MMMU-Pro (Vals) | Vals AI | 89.1% | – |
| MortgageTax | Vals AI | 65.3% | – |
| SAGE | Vals AI | 35.1% | – |
| AudioMC | Scale AI SEAL | 60.4% | – |
| AudioMC (text output) | Scale AI SEAL | 60.4% | – |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | 38.6%† | – |
| AA-3D | Artificial Analysis | 969 | – |
| Long context | |||
| AA-LCR | Artificial Analysis | 81.3% | 86.3% |
| MLCR | Artificial Analysis | 10.6% | – |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 157.4† | – |
| LiveBench 2.0 | LiveBench | 67.3%† | 76.7% |
| LiveBench 1.0 | LiveBench | 75.8% | – |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 40.9 | 55.1 |
| Vals Index | Vals AI | 56.0 | – |
| Vals Finance Index | Vals AI | 60.5% | – |
| Vals RSI Index | Vals AI | 19.9% | – |
| Vals Science Index | Vals AI | 35.8% | – |
| Vals Router Index | Vals AI | 56.0%† | – |
| AA Cyber Index | Artificial Analysis | 25.1 | 64.1 |
Data as of 2026-10-24. Best configuration of each model; every score links to its source on the model pages.
What changed
- Gemini 3.8 Flash: list price moves to $1.50 / $7.50 per 1M input / output tokens (announced).
- Kimi K3.1 Pro: BenchLeader Index 65.6 → 66.8.
- Kimi K3.1 Pro: 5 new results (FrontierCode 1.1 (AA), AA Cyber Index, CWE-Bench (AA)…).
- Gemini 3.8 Flash (high): 8 new results (Code Migration v1.1, Excel Modeling Benchmark v1.1, Finance Agent v2.1…).
- Kimi K3.1 Pro: first results.
- Gemini 3.8 Flash (high): 1 score revision.
- Gemini 3.8 Flash (high): 3 score revisions.
- Gemini 3.8 Flash (high): BenchLeader Index 63.7 → 64.5.
- Gemini 3.8 Flash (high): 1 new result (AudioMC (text output)).
- Gemini 3.8 Flash (high): 1 new result (SREBench); 2 score revisions.
Related comparisons
- Gemini 3.8 Flash vs Claude Opus 5.5
- Gemini 3.8 Flash vs Gemini 4 Argon
- Gemini 3.8 Flash vs Muse Wonder Full
- Kimi K3.1 Pro vs Claude Opus 5.5
- Kimi K3.1 Pro vs Gemini 4 Argon
- Kimi K3.1 Pro vs Muse Wonder Full
- Kimi K3.1 Pro vs Claude Fable 5.1
- Gemini 3.7 Flash vs Kimi K3.1 Pro
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
Gemini 3.8 Flash vs Kimi K3.1 Pro: questions
- Is Gemini 3.8 Flash better than Kimi K3.1 Pro?
- Gemini 3.8 Flash (high) and Kimi K3.1 Pro are neck and neck on quality (64.4 vs 66.8, within the ±7.3 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 2026-10-24, so check the category scores for your use.
- Which is cheaper, Gemini 3.8 Flash or Kimi K3.1 Pro, and will that change?
- Gemini 3.8 Flash is cheaper today: $1.50 against $4.00 per million tokens, blended at three input tokens per output token. Yes, that changes: Gemini 3.8 Flash's list price changes on 1 Jan 2027, and from then Gemini 3.8 Flash is cheaper ($3.00 vs $4.00 blended).
- Is Gemini 3.8 Flash better than Kimi K3.1 Pro for agents and tool use?
- Kimi K3.1 Pro scores higher in agentic tasks (67 vs 51 on the category index, where 50 is average). On CWE-Bench (AA), the top shared agents & tools benchmark, it is 52.5% for Gemini 3.8 Flash against 60.8% for Kimi K3.1 Pro.
- Which is better for long documents?
- Kimi K3.1 Pro scores higher on long-context benchmarks (68 vs 66). Both accept 1,048,576 tokens of context.
- Which has lower latency?
- Gemini 3.8 Flash (high) answers first: 25.1 s against 27.7 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
- Which is faster, Gemini 3.8 Flash or Kimi K3.1 Pro?
- Gemini 3.8 Flash streams faster: 141 against 81 output tokens per second.
- Do independent benchmarks agree on Gemini 3.8 Flash vs Kimi K3.1 Pro?
- Across the 18 benchmarks both have, Gemini 3.8 Flash leads 3, Kimi K3.1 Pro leads 15. Every overall index that rates both puts Kimi K3.1 Pro ahead.
- When was Kimi K3.1 Pro released?
- Kimi K3.1 Pro was released on 23 Oct 2026.