Gemini 3 Flash Preview vs Kimi K3
Kimi K3 leads Gemini 3 Flash Preview on coding, 62.3 to 43.7 on the Vibe Coding Index, and Gemini 3 Flash Preview costs 5.0x less per output token ($3.00 vs $15.00 per million). Updated October 21, 2026; 51 benchmarks have a result for both.
Gemini 3 Flash Preview or Kimi K3: which to pick
Pick Kimi K3 for coding: it scores 62.3 on the Vibe Coding Index against 43.7 for Gemini 3 Flash Preview.
Pick Gemini 3 Flash Preview for output tokens 5.0x cheaper ($3.00 vs $15.00 per million) and a lower cost per solved task ($0.37 against $0.81).
- Shared results
- 51
- Gemini 3 Flash Preview only
- 20
- Kimi K3 only
- 66
- Like-for-like categories
- 8 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
Kimi K3
Kimi K3 scores 62.3 against 43.7.
2 and 6 benchmarks behind the scores
Intelligence
AA Intelligence Index
Kimi K3
Kimi K3 leads, 43.6 against 26.3.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Kimi K3 has a AA Agentic Index result, 50.0.
Directional only
Reasoning
GPQA Diamond
Kimi K3
Kimi K3 leads, 92.9% against 87.9%.
Same board, both measured
Math
AIME
No call
Only Gemini 3 Flash Preview has a AIME result, 95.6%.
Directional only
Knowledge
MMLU Pro
Gemini 3 Flash Preview
Gemini 3 Flash Preview leads, 88.6% against 88.0%.
Same board, both measured
Web design
Design Arena: websites
Kimi K3
Kimi K3 leads, 1335 against 1196.
Same board, both measured
General
Vals Index
No call
Only Kimi K3 has a Vals Index result, 53.0%.
Directional only
Long documents
Listed context window
No call
Both take 1.05M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemini 3 Flash Preview
Gemini 3 Flash Preview $0.0020, Kimi K3 $0.011 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Gemini 3 Flash Preview
Gemini 3 Flash Preview $0.37, Kimi K3 $0.81.
Published attempt cost and pass rate
At a glance
- Coding index
- Gemini 3 Flash Preview 43.7 from 2 benchmarks, Kimi K3 62.3 from 6 benchmarks.
- Widest category
- Math, 29.1 points apart on average over 4 shared benchmarks.
- Widest single gap
- ProofBench: Gemini 3 Flash Preview 15.0% against Kimi K3 87.0%, 72.0 points apart on a 0 to 100 scale.
- Output price
- Gemini 3 Flash Preview $3.00 against Kimi K3 $15.00 per million output tokens, 5.0x apart.
- Context window
- Both take 1.05M tokens.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Gemini 3 Flash Preview | Bars | Kimi K3 | Ties |
|---|---|---|---|---|
| Coding | 0 | 8 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 11 | ||
| Reasoning | 2 | 7 | 1 tie | |
| Math | 0 | 4 | ||
| Knowledge | 5 | 2 | ||
| Web design | 0 | 4 | ||
| General | 0 | 6 | ||
| All shared boards | 7 | 43 | 1 tie |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index08
| Benchmark | Gemini 3 Flash Preview | Kimi K3 | Leader |
|---|---|---|---|
| SWE-bench Verified | 75.8% | Not measured | Only Gemini 3 Flash Preview measured |
| LiveBench coding | Not measured | 59.3% | Only Kimi K3 measured |
| LMArena WebDev | Not measured | 1655 | Only Kimi K3 measured |
| AA Coding Index | Not measured | 76.2 | Only Kimi K3 measured |
| LiveCodeBench (Vals AI) | 85.6% | 87.2% | Kimi K3 |
| SWE-bench Verified (Vals AI) | 75.0% | 93.4% | Kimi K3 |
| Terminal-Bench 4 (Vals AI) | Not measured | 17.2% | Only Kimi K3 measured |
| Vibe Code Bench (Vals AI) | 20.2% | 85.0% | Kimi K3 |
| Code migration (Vals AI) | 6.4% | 16.1% | Kimi K3 |
| ProgramBench (Vals AI) | 0.0% | 2.0% | Kimi K3 |
| IOI (Vals AI) | Not measured | 48.9% | Only Kimi K3 measured |
| Terminal-Bench 2.1 (Vals AI) | 53.9% | 80.9% | Kimi K3 |
| SWE-bench Multimodal (Vals AI) | Not measured | 44.2% | Only Kimi K3 measured |
| Vibe Code Bench 1-100 (Vals AI) | Not measured | 18.2% | Only Kimi K3 measured |
| CyberBench (Vals AI) | Not measured | 75.2% | Only Kimi K3 measured |
| LiveCodeBench (Artificial Analysis run) | 90.8% | Not measured | Only Gemini 3 Flash Preview measured |
| SciCode | Not measured | 59.5% | Only Kimi K3 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 38.6% | Not measured | Only Gemini 3 Flash Preview measured |
| Terminal-Bench | 64.3% | Not measured | Only Gemini 3 Flash Preview measured |
| FrontierCode | Not measured | 44.2% | Only Kimi K3 measured |
| FrontierSWE | Not measured | 25.9% | Only Kimi K3 measured |
| GSO-Bench | 9.8% | Not measured | Only Gemini 3 Flash Preview measured |
| WeirdML | 61.6% | 82.6% | Kimi K3 |
| ALE-Bench | 1367.2 | 1524.5 | Kimi K3 |
| LMArena Text: coding | Not measured | 1508 | Only Kimi K3 measured |
| LMArena Text: software and IT | Not measured | 1499 | Only Kimi K3 measured |
| LMArena WebDev: React | Not measured | 1670 | Only Kimi K3 measured |
| LMArena WebDev: HTML | Not measured | 1644 | Only Kimi K3 measured |
| LMArena WebDev: from an image | Not measured | 1579 | Only Kimi K3 measured |
| SciCode | 12.7% | Not measured | Only Gemini 3 Flash Preview measured |
| Neither model has a result on the other 9 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Gemini 3 Flash Preview | Kimi K3 | Leader |
|---|---|---|---|
| AA Intelligence Index | 26.3 | 43.6 | Kimi K3 |
| Epoch Capabilities Index | Not measured | 157.9 | Only Kimi K3 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index011
| Benchmark | Gemini 3 Flash Preview | Kimi K3 | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 50.0 | Only Kimi K3 measured |
| Design Arena: agents building web apps | 1110 | 1295 | Kimi K3 |
| Design Arena: agents building full-stack apps | 1063 | 1315 | Kimi K3 |
| Design Arena: agents building mobile apps | 1090 | 1269 | Kimi K3 |
| Design Arena: agents building Android apps | 1050 | 1250 | Kimi K3 |
| Design Arena: agents building Godot games | 1161 | 1223 | Kimi K3 |
| Design Arena: agents building games | Not measured | 1252 | Only Kimi K3 measured |
| Design Arena: HTML slides | Not measured | 1256 | Only Kimi K3 measured |
| Design Arena: PowerPoint slides | 1036 | 1273 | Kimi K3 |
| Design Arena: spreadsheets | Not measured | 1058 | Only Kimi K3 measured |
| LiveBench research | Not measured | 79.0% | Only Kimi K3 measured |
| LiveBench browser | Not measured | 16.0% | Only Kimi K3 measured |
| LiveBench long agentic | Not measured | 42.8% | Only Kimi K3 measured |
| Finance Agent (Vals AI) | 42.5% | 53.1% | Kimi K3 |
| Tax Agent Bench (Vals AI) | 11.8% | 33.4% | Kimi K3 |
| Legal Research Bench (Vals AI) | 18.3% | 46.1% | Kimi K3 |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 12.9% | Only Kimi K3 measured |
| Excel Modeling Benchmark (Vals AI) | 26.0% | 66.7% | Kimi K3 |
| BioMysteryBench (Vals AI) | Not measured | 72.6% | Only Kimi K3 measured |
| Terminal-Bench-Science (Vals AI) | Not measured | 1.4% | Only Kimi K3 measured |
| Time Horizon Index (Vals AI) | Not measured | 10.5% | Only Kimi K3 measured |
| τ²-Bench Telecom | 80.4% | Not measured | Only Gemini 3 Flash Preview measured |
| APEX-Agents | Not measured | 47.8% | Only Kimi K3 measured |
| BALROG | 48.1% | Not measured | Only Gemini 3 Flash Preview measured |
| DeepResearch Bench | 49.8% | Not measured | Only Gemini 3 Flash Preview measured |
| PostTrainBench | Not measured | 32.0% | Only Kimi K3 measured |
| Vending-Bench 2 | $3,635 | $5,165 | Kimi K3 |
| Neither model has a result on the other 14 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index27
| Benchmark | Gemini 3 Flash Preview | Kimi K3 | Leader |
|---|---|---|---|
| GPQA Diamond | 87.9% | 92.9% | Kimi K3 |
| LiveBench reasoning | Not measured | 90.7% | Only Kimi K3 measured |
| MMMU Pro (Vals AI) | 87.6% | 88.2% | Kimi K3 |
| GPQA Diamond (Artificial Analysis run) | 89.8% | 93.5% | Kimi K3 |
| Humanity's Last Exam (Artificial Analysis run) | 36.6% | 46.9% | Kimi K3 |
| GPQA Diamond (Epoch AI run) | 89.4% | 93.1% | Kimi K3 |
| ARC-AGI | 84.7% | 94.5% | Kimi K3 |
| ARC-AGI-2 | 33.6% | 60.4% | Kimi K3 |
| SimpleBench | 61.1% | 60.7% | Gemini 3 Flash Preview |
| Chess puzzles | 39.0% | 37.0% | Gemini 3 Flash Preview |
| Mystery game puzzles | 26.0% | 26.0% | Tie |
| VPCT | 72.6% | Not measured | Only Gemini 3 Flash Preview measured |
| LMArena Text: hard prompts | Not measured | 1495 | Only Kimi K3 measured |
| LMArena Text: expert | Not measured | 1520 | Only Kimi K3 measured |
| LMArena Text: hard prompts in English | Not measured | 1496 | Only Kimi K3 measured |
| Neither model has a result on the other 7 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | Gemini 3 Flash Preview | Kimi K3 | Leader |
|---|---|---|---|
| AIME | 95.6% | Not measured | Only Gemini 3 Flash Preview measured |
| MGSM (Vals AI) | 93.3% | Not measured | Only Gemini 3 Flash Preview measured |
| AA Math Index | 97.0 | Not measured | Only Gemini 3 Flash Preview measured |
| AIME 2025 (Artificial Analysis run) | 97.0% | Not measured | Only Gemini 3 Flash Preview measured |
| OTIS Mock AIME | 95.6% | 97.2% | Kimi K3 |
| FrontierMath, tiers 1 to 3 | 51.2% | 72.2% | Kimi K3 |
| FrontierMath, tier 4 | 17.1% | 39.0% | Kimi K3 |
| ProofBench | 15.0% | 87.0% | Kimi K3 |
| LMArena Text: math | Not measured | 1494 | Only Kimi K3 measured |
| LMArena Text: mathematical work | Not measured | 1505 | Only Kimi K3 measured |
| Neither model has a result on the other 3 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index52
| Benchmark | Gemini 3 Flash Preview | Kimi K3 | Leader |
|---|---|---|---|
| MMLU Pro | 88.6% | 88.0% | Gemini 3 Flash Preview |
| LegalBench (Vals AI) | 86.9% | 86.2% | Gemini 3 Flash Preview |
| CaseLaw (Vals AI) | 55.8% | Not measured | Only Gemini 3 Flash Preview measured |
| CorpFin (Vals AI) | 66.4% | 71.6% | Kimi K3 |
| TaxEval (Vals AI) | 73.9% | 75.7% | Kimi K3 |
| MortgageTax (Vals AI) | 68.7% | 66.3% | Gemini 3 Flash Preview |
| MedQA (Vals AI) | 95.8% | Not measured | Only Gemini 3 Flash Preview measured |
| MedCode (Vals AI) | 55.9% | 49.4% | Gemini 3 Flash Preview |
| MMLU Pro (Artificial Analysis run) | 89.0% | Not measured | Only Gemini 3 Flash Preview measured |
| SimpleQA Verified | 66.8% | 50.6% | Gemini 3 Flash Preview |
| GeoBench | 88.0% | Not measured | Only Gemini 3 Flash Preview measured |
| LMArena Text: science | Not measured | 1508 | Only Kimi K3 measured |
| LMArena Text: medicine and healthcare | Not measured | 1489 | Only Kimi K3 measured |
| LMArena Text: legal and government | Not measured | 1503 | Only Kimi K3 measured |
| LMArena Text: business and finance | Not measured | 1470 | Only Kimi K3 measured |
| FACTS Benchmark Suite | 63.4% | Not measured | Only Gemini 3 Flash Preview measured |
| Neither model has a result on the other 2 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | Gemini 3 Flash Preview | Kimi K3 | Leader |
|---|---|---|---|
| Design Arena: websites | 1196 | 1335 | Kimi K3 |
| Design Arena: UI components | Not measured | 1344 | Only Kimi K3 measured |
| Design Arena: game dev | 1166 | 1359 | Kimi K3 |
| Design Arena: data viz | Not measured | 1351 | Only Kimi K3 measured |
| Design Arena: 3D | 1184 | 1388 | Kimi K3 |
| Design Arena: all code categories | 1189 | 1360 | Kimi K3 |
| Design Arena: SVG | Not measured | 1302 | Only Kimi K3 measured |
| LiveBench design | Not measured | 77.2% | Only Kimi K3 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | Gemini 3 Flash Preview | Kimi K3 | Leader |
|---|---|---|---|
| Vals Index | Not measured | 53.0% | Only Kimi K3 measured |
| LiveBench data analysis | Not measured | 78.7% | Only Kimi K3 measured |
| Public Benefits Bench (Vals AI) | Not measured | 68.2% | Only Kimi K3 measured |
| SAGE (Vals AI) | 51.8% | 52.8% | Kimi K3 |
| MedScribe (Vals AI) | 69.9% | 88.0% | Kimi K3 |
| Vals Multimodal Index | 52.2% | 73.4% | Kimi K3 |
| IFBench | 78.0% | Not measured | Only Gemini 3 Flash Preview measured |
| Long context reasoning (AA-LCR) | 78.0% | 88.7% | Kimi K3 |
| DTBench | 89.1% | 91.2% | Kimi K3 |
| LMCA | 43.1% | 52.7% | Kimi K3 |
| Surface Evolver Bench | Not measured | 95.0% | Only Kimi K3 measured |
| Furniture assembly | Not measured | 34.2% | Only Kimi K3 measured |
| LMArena Text | Not measured | 1476 | Only Kimi K3 measured |
| LMArena Text: instruction following | Not measured | 1485 | Only Kimi K3 measured |
| LMArena Text: creative writing | Not measured | 1457 | Only Kimi K3 measured |
| LMArena Text: English | Not measured | 1481 | Only Kimi K3 measured |
| LMArena Text: non-English | Not measured | 1466 | Only Kimi K3 measured |
| LMArena Text: Chinese | Not measured | 1529 | Only Kimi K3 measured |
| LMArena Text: German | Not measured | 1490 | Only Kimi K3 measured |
| LMArena Text: Japanese | Not measured | 1494 | Only Kimi K3 measured |
| LMArena Text: Korean | Not measured | 1460 | Only Kimi K3 measured |
| LMArena Text: French | Not measured | 1492 | Only Kimi K3 measured |
| LMArena Text: Spanish | Not measured | 1472 | Only Kimi K3 measured |
| LMArena Text: Russian | Not measured | 1485 | Only Kimi K3 measured |
| LMArena Text: Polish | Not measured | 1458 | Only Kimi K3 measured |
| LMArena Text: multi-turn | Not measured | 1489 | Only Kimi K3 measured |
| LMArena Text: longer queries | Not measured | 1494 | Only Kimi K3 measured |
| LMArena Text: writing and language | Not measured | 1471 | Only Kimi K3 measured |
| LMArena Text: entertainment and media | Not measured | 1453 | Only Kimi K3 measured |
| Neither model has a result on the other 17 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemini 3 Flash Preview | Kimi K3 | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Gemini 3 Flash Preview costs less
Repository review
50K input + 3K output tokens
Gemini 3 Flash Preview costs less
Agent loop
200K input + 10K output tokens
Gemini 3 Flash Preview costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Google Gemini 3 Flash Preview | MoonshotAI Kimi K3 |
|---|---|---|
| Maker | Moonshot AI | |
| Weights | No public weights listed | Open weights |
| Released | December 17, 2025 | July 16, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $0.50 | $3.00 |
| Output $/Mtok | $3.00 | $15.00 |
| Coding index | 43.7 | 62.3 |
| Independent measurements behind it | 2 | 6 |
| Cost per solved task | $0.37 | $0.81 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemini 3 Flash Preview better than Kimi K3 for coding?
Pick Kimi K3 for coding: it scores 62.3 on the Vibe Coding Index against 43.7 for Gemini 3 Flash Preview. Pick Gemini 3 Flash Preview for output tokens 5.0x cheaper ($3.00 vs $15.00 per million) and a lower cost per solved task ($0.37 against $0.81).
Which is cheaper, Gemini 3 Flash Preview or Kimi K3?
Gemini 3 Flash Preview costs $0.50 per million input tokens and $3.00 per million output tokens; Kimi K3 costs $3.00 and $15.00. Per solved SWE-bench Verified task, Gemini 3 Flash Preview costs $0.37 and Kimi K3 $0.81.
Which has the bigger context window, Gemini 3 Flash Preview or Kimi K3?
Neither: both take 1.05M tokens.
How many benchmarks is the Gemini 3 Flash Preview vs Kimi K3 comparison based on?
51 benchmarks have a result for both models as of October 21, 2026. Gemini 3 Flash Preview's coding index rests on 2 independent benchmarks and Kimi K3's on 6. Where only one model has a result, the page says so instead of naming a winner.