Kimi K3 vs Step 5 Preview
Updated October 21, 2026. 53 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick Step 5 Preview for coding: it scores 71.4 on the Vibe Coding Index against 61.8 for Kimi K3.
Pick Kimi K3 when what matters is LMArena WebDev or Vibe Code Bench (Vals AI), where it leads.
- Shared results
- 53
- Kimi K3 only
- 64
- Step 5 Preview only
- 8
- Like-for-like categories
- 8 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
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, four public coding benchmarks
Step 5 Preview
Step 5 Preview scores 71.4 against 61.8.
2 benchmarks behind each score
Intelligence
AA Intelligence Index
Step 5 Preview
Step 5 Preview leads, 43.7 against 43.6.
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
No call
Only Kimi K3 has a GPQA Diamond result, 92.9%.
Directional only
Knowledge
MMLU Pro
No call
Only Kimi K3 has a MMLU Pro result, 88.0%.
Directional only
Web design
Design Arena: websites
No call
Only Kimi K3 has a Design Arena: websites result, 1336.
Directional only
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
Step 5 Preview
Kimi K3 $0.0062, Step 5 Preview $0.0024 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Kimi K3 has the number, $0.81.
Directional only
At a glance
- Coding index
- Kimi K3 61.8 from 2 benchmarks, Step 5 Preview 71.4 from 2 benchmarks.
- Widest category
- Math, 19.5 points apart on average over 3 shared benchmarks.
- Widest single gap
- ProofBench: Kimi K3 87.0% against Step 5 Preview 42.0%, 45.0 points apart on a 0 to 100 scale.
- Output price
- Kimi K3 $11.936 against Step 5 Preview $2.70 per million output tokens, 4.4x 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 | Kimi K3 | Bars | Step 5 Preview | Ties |
|---|---|---|---|---|
| Coding | 10 | 3 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 7 | 2 | ||
| Reasoning | 5 | 0 | ||
| Math | 3 | 0 | ||
| Knowledge | 4 | 0 | ||
| Web design | 1 | 0 | ||
| General | 17 | 0 | ||
| All shared boards | 47 | 6 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index103
| Benchmark | Kimi K3 | Step 5 Preview | Leader |
|---|---|---|---|
| LiveBench coding | 59.3% | 85.6% | Step 5 Preview |
| LMArena WebDev | 1655 | 1567 | Kimi K3 |
| AA Coding Index | 76.2 | Not measured | Only Kimi K3 measured |
| LiveCodeBench (Vals AI) | 87.2% | Not measured | Only Kimi K3 measured |
| SWE-bench Verified (Vals AI) | 93.4% | Not measured | Only Kimi K3 measured |
| Terminal-Bench 4 (Vals AI) | 17.2% | 31.8% | Step 5 Preview |
| Vibe Code Bench (Vals AI) | 85.0% | 70.4% | Kimi K3 |
| Code migration (Vals AI) | 16.1% | 39.0% | Step 5 Preview |
| ProgramBench (Vals AI) | 2.0% | Not measured | Only Kimi K3 measured |
| IOI (Vals AI) | 48.9% | 38.1% | Kimi K3 |
| Terminal-Bench 2.1 (Vals AI) | 80.9% | Not measured | Only Kimi K3 measured |
| SWE-bench Multimodal (Vals AI) | 44.2% | 40.8% | Kimi K3 |
| Vibe Code Bench 1-100 (Vals AI) | 18.2% | Not measured | Only Kimi K3 measured |
| CyberBench (Vals AI) | 75.2% | Not measured | Only Kimi K3 measured |
| SciCode | 59.5% | 58.9% | Kimi K3 |
| FrontierCode | 44.2% | Not measured | Only Kimi K3 measured |
| FrontierSWE | 25.9% | Not measured | Only Kimi K3 measured |
| WeirdML | 82.6% | Not measured | Only Kimi K3 measured |
| ALE-Bench | 1524.5 | Not measured | Only Kimi K3 measured |
| LMArena Text: coding | 1508 | 1485 | Kimi K3 |
| LMArena Text: software and IT | 1499 | 1473 | Kimi K3 |
| LMArena WebDev: React | 1670 | 1583 | Kimi K3 |
| LMArena WebDev: HTML | 1644 | 1556 | Kimi K3 |
| LMArena WebDev: from an image | 1579 | 1550 | Kimi K3 |
| Neither model has a result on the other 14 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Kimi K3 | Step 5 Preview | Leader |
|---|---|---|---|
| AA Intelligence Index | 43.6 | 43.7 | Step 5 Preview |
| Epoch Capabilities Index | 157.9 | Not measured | Only Kimi K3 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index72
| Benchmark | Kimi K3 | Step 5 Preview | Leader |
|---|---|---|---|
| AA Agentic Index | 50.0 | Not measured | Only Kimi K3 measured |
| Design Arena: agents building web apps | 1296 | Not measured | Only Kimi K3 measured |
| Design Arena: agents building full-stack apps | 1315 | Not measured | Only Kimi K3 measured |
| Design Arena: agents building mobile apps | 1267 | Not measured | Only Kimi K3 measured |
| Design Arena: agents building Android apps | 1256 | Not measured | Only Kimi K3 measured |
| Design Arena: agents building Godot games | 1223 | Not measured | Only Kimi K3 measured |
| Design Arena: agents building games | 1252 | Not measured | Only Kimi K3 measured |
| Design Arena: HTML slides | 1256 | Not measured | Only Kimi K3 measured |
| Design Arena: PowerPoint slides | 1273 | Not measured | Only Kimi K3 measured |
| Design Arena: spreadsheets | 1058 | Not measured | Only Kimi K3 measured |
| LiveBench research | 79.0% | 72.8% | Kimi K3 |
| LiveBench browser | 16.0% | 24.0% | Step 5 Preview |
| LiveBench long agentic | 42.8% | 27.5% | Kimi K3 |
| SREBench (Vals AI) | Not measured | 0.4% | Only Step 5 Preview measured |
| Finance Agent (Vals AI) | 53.1% | 50.7% | Kimi K3 |
| Tax Agent Bench (Vals AI) | 33.4% | 27.3% | Kimi K3 |
| Legal Research Bench (Vals AI) | 46.1% | 40.4% | Kimi K3 |
| Harvey's Legal Agent Benchmark (Vals AI) | 12.9% | Not measured | Only Kimi K3 measured |
| Excel Modeling Benchmark (Vals AI) | 66.7% | 57.1% | Kimi K3 |
| BioMysteryBench (Vals AI) | 72.6% | 67.4% | Kimi K3 |
| Terminal-Bench-Science (Vals AI) | 1.4% | 2.9% | Step 5 Preview |
| Vals Science Index | Not measured | 29.6% | Only Step 5 Preview measured |
| Time Horizon Index (Vals AI) | 10.5% | Not measured | Only Kimi K3 measured |
| APEX-Agents | 47.8% | Not measured | Only Kimi K3 measured |
| PostTrainBench | 32.0% | Not measured | Only Kimi K3 measured |
| Vending-Bench 2 | $5,165 | Not measured | Only Kimi K3 measured |
| Neither model has a result on the other 13 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Kimi K3 | Step 5 Preview | Leader |
|---|---|---|---|
| GPQA Diamond | 92.9% | Not measured | Only Kimi K3 measured |
| LiveBench reasoning | 90.7% | 83.8% | Kimi K3 |
| MysteryMechanism (Vals AI) | Not measured | 18.5% | Only Step 5 Preview measured |
| MMMU Pro (Vals AI) | 88.2% | Not measured | Only Kimi K3 measured |
| GPQA Diamond (Artificial Analysis run) | 93.5% | Not measured | Only Kimi K3 measured |
| Humanity's Last Exam (Artificial Analysis run) | 46.9% | 46.5% | Kimi K3 |
| GPQA Diamond (Epoch AI run) | 93.1% | Not measured | Only Kimi K3 measured |
| ARC-AGI | 94.5% | Not measured | Only Kimi K3 measured |
| ARC-AGI-2 | 60.4% | Not measured | Only Kimi K3 measured |
| SimpleBench | 60.7% | Not measured | Only Kimi K3 measured |
| Chess puzzles | 37.0% | Not measured | Only Kimi K3 measured |
| Mystery game puzzles | 26.0% | Not measured | Only Kimi K3 measured |
| LMArena Text: hard prompts | 1495 | 1461 | Kimi K3 |
| LMArena Text: expert | 1520 | 1485 | Kimi K3 |
| LMArena Text: hard prompts in English | 1496 | 1454 | Kimi K3 |
| LMArena Vision: diagrams | Not measured | 1308 | Only Step 5 Preview measured |
| LMArena Vision: homework | Not measured | 1265 | Only Step 5 Preview measured |
| Neither model has a result on the other 4 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | Kimi K3 | Step 5 Preview | Leader |
|---|---|---|---|
| OTIS Mock AIME | 97.2% | Not measured | Only Kimi K3 measured |
| FrontierMath, tiers 1 to 3 | 72.2% | Not measured | Only Kimi K3 measured |
| FrontierMath, tier 4 | 39.0% | Not measured | Only Kimi K3 measured |
| ProofBench | 87.0% | 42.0% | Kimi K3 |
| LMArena Text: math | 1494 | 1458 | Kimi K3 |
| LMArena Text: mathematical work | 1505 | 1460 | Kimi K3 |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Kimi K3 | Step 5 Preview | Leader |
|---|---|---|---|
| MMLU Pro | 88.0% | Not measured | Only Kimi K3 measured |
| LegalBench (Vals AI) | 86.2% | Not measured | Only Kimi K3 measured |
| CorpFin (Vals AI) | 71.6% | Not measured | Only Kimi K3 measured |
| TaxEval (Vals AI) | 75.7% | Not measured | Only Kimi K3 measured |
| MortgageTax (Vals AI) | 66.3% | Not measured | Only Kimi K3 measured |
| MedCode (Vals AI) | 49.4% | Not measured | Only Kimi K3 measured |
| SimpleQA Verified | 50.6% | Not measured | Only Kimi K3 measured |
| LMArena Text: science | 1508 | 1454 | Kimi K3 |
| LMArena Text: medicine and healthcare | 1489 | 1439 | Kimi K3 |
| LMArena Text: legal and government | 1503 | 1437 | Kimi K3 |
| LMArena Text: business and finance | 1470 | 1435 | Kimi K3 |
| Neither model has a result on the other 6 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Kimi K3 | Step 5 Preview | Leader |
|---|---|---|---|
| Design Arena: websites | 1336 | Not measured | Only Kimi K3 measured |
| Design Arena: UI components | 1345 | Not measured | Only Kimi K3 measured |
| Design Arena: game dev | 1361 | Not measured | Only Kimi K3 measured |
| Design Arena: data viz | 1350 | Not measured | Only Kimi K3 measured |
| Design Arena: 3D | 1388 | Not measured | Only Kimi K3 measured |
| Design Arena: all code categories | 1361 | Not measured | Only Kimi K3 measured |
| Design Arena: SVG | 1301 | Not measured | Only Kimi K3 measured |
| LiveBench design | 77.2% | 76.9% | Kimi K3 |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index170
| Benchmark | Kimi K3 | Step 5 Preview | Leader |
|---|---|---|---|
| Vals Index | 53.0% | Not measured | Only Kimi K3 measured |
| LiveBench data analysis | 78.7% | 63.5% | Kimi K3 |
| Public Benefits Bench (Vals AI) | 68.2% | 58.1% | Kimi K3 |
| SAGE (Vals AI) | 52.8% | Not measured | Only Kimi K3 measured |
| MedScribe (Vals AI) | 88.0% | Not measured | Only Kimi K3 measured |
| Vals Multimodal Index | 73.4% | Not measured | Only Kimi K3 measured |
| Long context reasoning (AA-LCR) | 88.7% | 88.3% | Kimi K3 |
| DTBench | 91.2% | Not measured | Only Kimi K3 measured |
| LMCA | 52.7% | Not measured | Only Kimi K3 measured |
| Surface Evolver Bench | 95.0% | Not measured | Only Kimi K3 measured |
| Furniture assembly | 34.2% | Not measured | Only Kimi K3 measured |
| LMArena Text | 1476 | 1440 | Kimi K3 |
| LMArena Text: instruction following | 1485 | 1438 | Kimi K3 |
| LMArena Text: creative writing | 1457 | 1409 | Kimi K3 |
| LMArena Vision | Not measured | 1265 | Only Step 5 Preview measured |
| LMArena Text: English | 1481 | 1447 | Kimi K3 |
| LMArena Text: non-English | 1466 | 1428 | Kimi K3 |
| LMArena Text: Chinese | 1529 | 1500 | Kimi K3 |
| LMArena Text: German | 1490 | Not measured | Only Kimi K3 measured |
| LMArena Text: Japanese | 1494 | 1383 | Kimi K3 |
| LMArena Text: Korean | 1460 | Not measured | Only Kimi K3 measured |
| LMArena Text: French | 1492 | 1438 | Kimi K3 |
| LMArena Text: Spanish | 1472 | 1441 | Kimi K3 |
| LMArena Text: Russian | 1485 | 1433 | Kimi K3 |
| LMArena Text: Polish | 1458 | Not measured | Only Kimi K3 measured |
| LMArena Text: multi-turn | 1489 | 1437 | Kimi K3 |
| LMArena Text: longer queries | 1494 | 1449 | Kimi K3 |
| LMArena Text: writing and language | 1471 | 1425 | Kimi K3 |
| LMArena Text: entertainment and media | 1453 | 1412 | Kimi K3 |
| LMArena Vision: English | Not measured | 1290 | Only Step 5 Preview measured |
| LMArena Vision: reading text | Not measured | 1282 | Only Step 5 Preview measured |
| Neither model has a result on the other 15 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Kimi K3 | Step 5 Preview | 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
Step 5 Preview costs less
Repository review
50K input + 3K output tokens
Kimi K3 costs less
Agent loop
200K input + 10K output tokens
Kimi K3 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 | MoonshotAI Kimi K3 | StepFun Step 5 Preview |
|---|---|---|
| Maker | Moonshot AI | StepFun |
| Weights | Open weights | Open weights |
| Released | July 16, 2026 | October 8, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $0.239 | $1.00 |
| Output $/Mtok | $11.936 | $2.70 |
| Coding index | 61.8 | 71.4 |
| Independent measurements behind it | 2 | 2 |
| Cost per solved task | $0.81 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Kimi K3 better than Step 5 Preview for coding?
Pick Step 5 Preview for coding: it scores 71.4 on the Vibe Coding Index against 61.8 for Kimi K3. Pick Kimi K3 when what matters is LMArena WebDev or Vibe Code Bench (Vals AI), where it leads.
Which is cheaper, Kimi K3 or Step 5 Preview?
Kimi K3 costs $0.239 per million input tokens and $11.936 per million output tokens; Step 5 Preview costs $1.00 and $2.70. Cost per solved task is known for Kimi K3 only.
Which has the bigger context window, Kimi K3 or Step 5 Preview?
Neither: both take 1.05M tokens.
How many benchmarks is the Kimi K3 vs Step 5 Preview comparison based on?
53 benchmarks have a result for both models as of October 21, 2026. Kimi K3's coding index rests on 2 independent benchmarks and Step 5 Preview's on 2. Where only one model has a result, the page says so instead of naming a winner.